CN105493180A - Electronic device and method for voice recognition - Google Patents

Electronic device and method for voice recognition Download PDF

Info

Publication number
CN105493180A
CN105493180A CN201480047495.1A CN201480047495A CN105493180A CN 105493180 A CN105493180 A CN 105493180A CN 201480047495 A CN201480047495 A CN 201480047495A CN 105493180 A CN105493180 A CN 105493180A
Authority
CN
China
Prior art keywords
voice
speech recognition
voice recognition
recognition equipment
processor
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201480047495.1A
Other languages
Chinese (zh)
Other versions
CN105493180B (en
Inventor
李相勋
姜赫
金炅泰
诸成民
郑晳荣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Samsung Electronics Co Ltd
Original Assignee
Samsung Electronics Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Samsung Electronics Co Ltd filed Critical Samsung Electronics Co Ltd
Publication of CN105493180A publication Critical patent/CN105493180A/en
Application granted granted Critical
Publication of CN105493180B publication Critical patent/CN105493180B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G10L17/22—Interactive procedures; Man-machine interfaces
    • G10L17/24—Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3206—Monitoring of events, devices or parameters that trigger a change in power modality
    • G06F1/3231—Monitoring the presence, absence or movement of users
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/32—Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G10L17/04—Training, enrolment or model building
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G10L17/06—Decision making techniques; Pattern matching strategies
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The present invention relates to a method and an electronic device for changing a dynamic screen layout. A method using an electronic device according to various embodiments of the present invention may comprise the steps of: one or more devices of a first voice recognition device and a second voice recognition device acquiring a first voice; recognizing an additionally recognized second voice through an external electronic device when a predetermined command is included in the first voice acquired by the first voice recognition device; recognizing an additionally recognized second voice when a predetermined command is included the first voice acquired by the second voice recognition device; and performing a related operation on the basis of the recognized second voice.

Description

For electronic installation and the method for speech recognition
Technical field
The disclosure relates to electronic installation, and various embodiment relates to the configuration for speech recognition.
Background technology
Generally speaking, people can have themselves distinctive sound, and voice itself can be used as authentication means.
Speech recognition equipment by use the voice that gathered specific people and about the speech recognition modeling of the information of voice to identify the voice of specific people, person's checking that this is referred to as language.Speech recognition equipment is by using as the speech recognition modeling of the voice and training in advance that identify multiple people is to the voice of the person that distinguishes language, and this is referred to as language, and person identifies.
The speech recognition equipment that the person that makes term checking or language person identify carrys out training utterance model of cognition by using particular phrase, and only identifies voice when specific language person says particular phrase in this case, thus has higher security performance.
In addition, by using, speech recognition equipment only identifies that the isolated word recognition methods of predetermined certain words is to identify voice.Isolated word recognition methods refers to the template that produces each certain words and by the method for described template compared with the voice of input.Use the speech recognition equipment of isolated word recognition methods only to identify predetermined certain words, therefore there is higher phonetic recognization rate and there is the lower speech recognition mortality due to ground unrest reason.Correspondingly, isolated word recognition methods and all voice can be converted into the large vocabulary speech recognition (LVSR) of text and natural-sounding identification comparatively speaking has less calculated amount and uses less internal memory, make easily isolated word pronunciation recognition methods to be used for mobile terminal device.
Summary of the invention
Technical matters
As mentioned above, speech recognition equipment is identified by the person that makes term checking or language person and identifies voice or by using isolated word recognition methods to identify voice.
But traditional voice recognition device has the problem being difficult to perform the audio recognition method with intensive when low-power processor is mounted.
In addition, because high-performance pre-service and high-performance speech recognition are performed, so when high-performance processor is mounted, traditional voice recognition device has the shortcoming of large power consumption.
Technical scheme
Correspondingly, various embodiment of the present invention is provided for electronic installation and method by using two or more processors to identify voice, wherein, two or more processors described comprise the processor with low-power consumption and the processor performing high-performance speech recognition.
According to various embodiments of the present invention, in order to actualizing technology scheme, provide a kind of method using electronic installation.Described method comprises: obtain the first voice by least one device in the first speech recognition equipment and the second speech recognition equipment; When the first voice obtained by the first speech recognition equipment comprise predetermined command, the second voice additionally identified by external electronic identification; When the first voice obtained by second people's speech recognition equipment comprise predetermined command, identify extra the second voice identified; Corresponding operating is performed based on the second voice identified.
According to various embodiments of the present invention, electronic installation comprises: at least one device in the first speech recognition equipment and the second speech recognition equipment, wherein, when the first voice obtained by the first speech recognition equipment comprise predetermined command, second voice of extra identification are identified by external electronic, and when the first voice obtained by second people's speech recognition equipment comprise predetermined command, second voice of extra identification are identified, and then associative operation is performed based on the second voice identified.
Beneficial effect
According to various embodiments of the present invention, can keep having low-power consumption and the speech recognition system being always in holding state performs the natural-sounding identification of the various inquiries that can respond user, respond for the special sound order of the application requiring fast operating to react, even if be speech recognition and the voice signal distortion that inputs also performs the speech recognition with high phonetic recognization rate.
Accompanying drawing explanation
Fig. 1 illustrates the network environment of the electronic installation comprised according to various embodiment;
Fig. 2 illustrates the configuration of the first voice recognition processor according to various embodiment and the second voice recognition processor;
Fig. 3 illustrates the configuration of the first voice recognition processor according to various embodiment and the second voice recognition processor;
Fig. 4 illustrates the configuration of the first voice recognition processor according to various embodiment and the second voice recognition processor;
Fig. 5 illustrates the configuration of the first voice recognition processor according to various embodiment and the second voice recognition processor;
Fig. 6 illustrates the configuration of the first voice recognition processor, the second voice recognition processor and the 3rd voice recognition processor according to various embodiment;
Fig. 7 illustrates the configuration of the first voice recognition processor, the second voice recognition processor and the 3rd voice recognition processor according to various embodiment;
Fig. 8 illustrates the configuration of the pretreatment unit according to various embodiment;
Fig. 9 illustrates the process flow diagram being performed the process of speech recognition according to the controller of various embodiment by the first voice recognition processor or the second voice recognition processor;
Figure 10 illustrates the process flow diagram being performed the process of speech recognition according to the controller of various embodiment by the first voice recognition processor or the second voice recognition processor;
Figure 11 illustrates the process flow diagram being performed the process of speech recognition according to the controller of various embodiment by the first voice recognition processor or the second voice recognition processor;
Figure 12 illustrates the process flow diagram being performed the process of speech recognition according to the controller of various embodiment by the first voice recognition processor or the second voice recognition processor;
Figure 13 illustrates the process being performed speech recognition by the first voice recognition processor, the second voice recognition processor and the 3rd voice recognition processor according to various embodiment;
Figure 14 illustrates the process being performed speech recognition by the first voice recognition processor, the second voice recognition processor and the 3rd voice recognition processor according to various embodiment;
Figure 15 illustrates the process being performed speech recognition by the first voice recognition processor, the second voice recognition processor and the 3rd voice recognition processor according to various embodiment;
Figure 16 illustrates the process of being upgraded by speech recognition modeling by the 3rd voice recognition processor according to various embodiment;
Figure 17 is the block diagram of the electronic installation according to various embodiment.
Embodiment
Hereinafter, various embodiment of the present invention will be described by reference to the accompanying drawings.Can revise the present invention in a variety of manners, and the present invention can comprise various embodiment, but in the accompanying drawings instantiation be described and in the description instantiation be described.But instructions is not intended to limit the invention to specific embodiment, should be understood that the change of term design of the present invention and technical scope, equivalent and replacement are all included in the present invention.For in the description of accompanying drawing, same or analogous drawing reference numeral is used to specify same or analogous element.
Hereinafter, the term used in various embodiments of the present invention " comprises " or " can comprise " instruction exists disclosed function, operation or element, does not limit for one or more function of increase, operation or element.In the present invention, such as " to comprise " or the term of " having " can be understood to represent specific feature, numeral, step, operation, element, assembly or these combination, but can not be understood to get rid of increases one or more further feature, numeral, step, operation, element, the existence of assembly or these combination or possibility.
Term "or" in various embodiments of the present invention means to comprise instruction element in the element indicating and be disclosed or all elements.Such as, expressing " A or B " can comprise A, can comprise B or can comprise A and B.
The expression of such as " first ", " second " etc. in various embodiments of the present invention can modify various element in various embodiments, but can not limit corresponding element.Such as, the expression above not order of limiting element and/or importance.The object of expression above only for element is distinguished mutually with other element.Such as, although first user device and the second user's set are all user's sets, both indicate different user's sets.Such as, without departing from the scope of the invention, the first element can be named as the second element.Similarly, the second element also can be named as the first element.
Should note, if describe an element to be " coupled " or to ' attach ' to another element, then the first element can be directly coupled or be connected to the second element, and can between the first element and the second element " coupling " or " connection " the 3rd element.On the contrary, when an element " when being directly coupled " or " directly connected " to another element, be will be understood that there is not the 3rd element between the first element and the second element.
Term is in various embodiments of the present invention used to describe specific embodiment, but is not intended to limit the present invention.As used herein, unless context clearly separately has instruction, otherwise singulative intention also comprises plural form.
Unless limited by different way, otherwise all terms comprising technical term or scientific terminology as used herein have the implication identical with the understanding of those skilled in the art in the invention.Term as limited in normally used dictionary, unless be clearly defined in the present invention, otherwise by being interpreted as, there is the implication identical with the situational meaning in correlative technology field and by not being interpreted as, there is Utopian implication or too formal implication.
Electronic installation according to various embodiments of the present invention can be the device with Presentation Function.Such as, electronic installation can comprise at least one in following item: smart phone, tablet personal computer (PC), smart phone, visual telephone, E-book reader, Desktop PC, PC on knee, net book, personal digital assistant (PDA), portable media player (PMP), MP3 player, portable medical device, camera, wearable device are (such as, wear-type device (HMD) (such as, electronic glasses), Electronic Clothes, electronics bracelet, electronics necklace, electronic application accessory, electronics are tatooed or intelligent watch).
According to some embodiments, electronic installation can be the controlling intelligent household appliances with Presentation Function.Controlling intelligent household appliances can comprise at least one in following item: such as, televisor, digital video disc (DVD) player, audio player, refrigerator, air-conditioning, suction cleaner, baking box, micro-wave oven, washing machine, air purifier, Set Top Box, TV box (such as, Samsung HomeSync tM, apple TV tMor Google TV tM), game machine, electronic dictionary, electron key, video camera or digital photo frame.
According to some embodiments, electronic installation can comprise at least one in following item: various medical treatment device (such as, magnetic resonance angiography (MRA) scanner, magnetic resonance imaging (MRI) scanner, computed tomography (CT) scanner, scanning machine, Ultrasound Instrument etc.), guider, GPS (GPS) receiver, event data recorder (EDR), flight data recorder (FDR), vehicle infotainment device, for boats and ships electronic equipment (such as, marine navigation device, gyrostatic compass etc.), avionic device, safety feature, the head unit of vehicle, industrial robot or domestic robot, ATM (Automatic Teller Machine) (ATM) in financial institution or the point of sale (POS) in shop.
According to some embodiments, electronic installation can comprise at least one in following item: comprise a part for the furniture of Presentation Function or building/structure, CAXA, electronic signature receiving trap, projector and various types of measurement mechanism (such as, water meter, ammeter, gas meter, radio wave table etc.).Electronic installation according to various embodiments of the present invention can be the combination of the one or more devices in above-mentioned various device.In addition, electronic installation according to various embodiments of the present invention can be flexible apparatus.In addition, electronic installation is according to various embodiments of the present invention not limited to said apparatus.
Hereinafter, the electronic installation according to various embodiment is described with reference to the accompanying drawings.The term " user " used in various embodiments can indicate the people using electronic installation or the device (such as, artificial intelligence electronic installation) using electronic installation.
Fig. 1 illustrates the network environment 100 of the electronic installation 101 comprised according to various embodiment.
With reference to Fig. 1, electronic installation 101 can comprise bus 110, processor 120, storer 130, input/output interface 140, display 150, communication interface 160, first voice recognition processor 170 and the second voice recognition processor 180.
Bus 110 can be for being connected to each other by said elements or the circuit of transmission information (such as, control message) between described element.
Controller 120 by such as bus 110 from other element above-mentioned (such as, storer 130, input/output interface 140, display 150, communication interface 160, first voice recognition processor 170, second voice recognition processor 180 etc.) receive order, decoding to the order received and performing according to the order of decoding calculates or data processing.
Storer 130 can store order that is that receive from processor 120 or other element (such as, input/output interface 140, display 150, communication interface 160, first voice recognition processor 170, second voice recognition processor 180 etc.) or that produced by processor 120 or other element described or data.Storer 130 can comprise programming module (such as, kernel 131, middleware 132, application programming interfaces (API) 133, application 134 etc.).Each module in above-mentioned programming module can be formed by the combination of at least two in software, firmware, hardware or software, firmware, hardware.
Kernel 131 can control or manage for performing at all the other programming modules (such as, middleware 132, API133 and application 134) in the operation that realizes or the system resource (such as, bus 110, processor 120, storer 130 etc.) of function.In addition, kernel 131 can provide interface, wherein, middleware 132, API133 and application 134 by described interface accessing electronic installation 101 independent element with control or management element.
Middleware 132 can be used as medium, makes API133 or application 134 communicate to send/receive data with kernel 131.In addition, about the request for operation received from application 134, middleware 132 can such as determine the system resource of use electronic installation 101 (such as at least one application in application 134 by use, bus 110, processor 120, storer 130 etc.) the method for order control (such as, carrying out dispatching or load balance) request for operation.
API133 is interface and can comprises such as at least one interface of document control, window control, image procossing, text control etc. or function (such as, order), wherein, 134 functions provided from kernel 131 or middleware 132 by described Interface Controller are provided.
According to various embodiment, application 134 can comprise Short Message Service (SMS)/multimedia information service (MMS) application, e-mail applications, calendar application, alarm clock application, healthcare application (such as, for providing the application of atmospheric pressure, humidity or temperature information).Extraly or alternatively, application 134 can be the application relevant with the message exchange between electronic installation 101 and external electronic (such as, electronic installation 104).The application information-related with exchange can comprise such as external electronic or the device management for managing external electronic (such as, electronic installation 104) and apply.
Such as, notice forwards application and can comprise by other application at electronic installation 101 (such as, SMS/MMS application, e-mail applications, healthcare application or environmental information application) in the announcement information that produces be sent to the function of external electronic (such as, electronic installation 104).Extraly or alternatively, notice forwards application and such as the announcement information of reception can be supplied to user from external electronic (such as, electronic installation 104) reception notification information.Device management application can such as manage (such as, install, delete or upgrade) for the function at least partially in following item: communicate (such as with electronic installation 101, On/Off external electronic itself (or some elements of external electronic) or adjustment display brightness (or resolution)) external electronic (such as, electronic installation 104), the application that operates in external electronic or the service (such as, telephone calling service or messenger service) provided by external electronic.
According to various embodiment, the application that application 134 can comprise the attribute (such as, the type of electronic installation) according to external electronic (such as, electronic installation 104) and specify.Such as, when external electronic is MP3 player, application 134 can comprise the application relevant with the reproduction of music.Similarly, when external electronic is portable medical device, application 134 can comprise the application relevant with medical treatment and nursing.According to embodiment, application 134 can comprise at least one application in following application: the application of specifying in electronic installation 101 or the application received from external electronic (such as, server 106 or electronic installation 104).
The order that IO interface 140 can such as will be inputted by input/output device (such as, sensor, keyboard or touch-screen) by user by bus 110 or data are sent to processor 120, storer 130, communication interface 160, first voice recognition processor 170 and the second voice recognition processor 180.Such as, input/output interface 140 can provide the data relevant with the touch of the user inputted by touch-screen to processor 120.In addition, input/output interface 140 by input/output device (such as, loudspeaker or display) output example as the order received from processor 120, storer 130, communication interface 160, first voice recognition processor 170 or the second voice recognition processor 180 by bus 110 or data.Such as, input/output interface 140 exports the speech data processed by processor 120 to user by loudspeaker.
Display 150 can show various information (such as, multi-medium data or text data) to user.
Communication interface 160 can connect the communication between electronic installation 101 and external electronic (such as, electronic installation 104 or server 106).Such as, by wire communication or radio communication, communication interface 160 is connected to network 162 to communicate with external electronic.Radio communication can comprise at least one in following item: such as, Wi-Fi (Wireless Fidelity), BT (bluetooth), NFC (near-field communication), GPS (GPS) and cellular communication (such as, LTE, LTE-A, CDMA, WCDMA, UMTS, WiBro, GSM etc.).Wire communication can comprise at least one in following item: such as, USB (USB (universal serial bus)), HDMI (high-definition media interface), proposed standard 232 (RS-232) and POTS (plain old telephone service).
According to embodiment, network 162 can be communication network.Communication network can comprise at least one in following item: computer network, internet, Internet of Things and telephone network.According to embodiment, the agreement (such as, transport layer protocol, data link layer protocol or physical layer protocol) for the communication between electronic installation 101 and external electronic can be supported at least one in following item: application 134, application programming interfaces 133, middleware 132, kernel 131 and communication interface 160.
First voice recognition processor 170 and/or the second voice recognition processor 180 can carry out processing at least some information obtained from other element (such as, processor 120, storer 130, input/output interface 140, communication interface 160 etc.) and provide the information processed by various method to user.
Such as, the first voice recognition processor 170 receives the first voice from input/output interface 140 by making purpose processor 120 or not relying on processor 120 and determines whether comprise the first order the first voice.According to various embodiments of the present invention, carry out default first order by certain words or the first order can be set by user.
When the first voice comprise the first order, first voice recognition processor 170 can by the second voice transfer of additionally receiving to external electronic (such as, electronic installation 104 or server 106), therefore external electronic can perform speech recognition to the second voice.
In addition, after the first voice are identified and determine whether comprise the first order in the first voice, when the first voice comprise the first order, the second voice that the second voice recognition processor 180 identifiable design additionally receives the voice command determining whether to comprise in the second voice pre-stored concentrates the second included order.According to various embodiments of the present invention, the second command set can comprise multiple word.
When the second voice comprise the second order, the second voice recognition processor 180 can perform orders corresponding operation to second.According to another embodiment, the second voice recognition processor 180 can order the signal of corresponding operation to be sent to processor 120 to second by being used for performing, and therefore processor 120 can perform described operation.
Fig. 2 illustrates the configuration of the first voice recognition processor according to various embodiment and the second voice recognition processor.
With reference to Fig. 2, electronic installation 101 can comprise the first voice recognition processor 170, second voice recognition processor 180, microphone 400, loudspeaker 410 and audio-frequency module 420.
According to various embodiment, microphone 400 can received speech signal.In the description, microphone can be called voice-input unit.
Loudspeaker 410 can comprise loudspeaker and export voice signal.In addition, the exportable sound signal produced by execution application or program of loudspeaker 410.In this manual, loudspeaker can be called audio output unit.
Audio-frequency module 420 can be connected to the first voice recognition processor 170, second voice recognition processor 180, microphone 400 and loudspeaker 410 to perform process analog voice signal being converted to audio digital signals or audio digital signals being converted to analog voice signal.In addition, audio-frequency module 420 can to the digital signal executive signal process (such as, automatic growth control, equalization etc.) changed out.Audio-frequency module 420 can send/receive the voice signal of application or program.
Audio-frequency module 420 can be embodied as and receive independent electric power or optionally implement audio-frequency module 420.According to another embodiment, audio-frequency module 420 can be realized in each processor in the first voice recognition processor 170 and the second voice recognition processor 180 and without the need to receiving independent electric power.
First voice recognition processor 170 can comprise the first voice recognition processing unit 110, first voice recognition processing unit 110 can comprise the first processing unit 111, first speech recognition modeling storage unit 112 and the first voice recognition unit 113.In the description, speech recognition modeling storage unit can be called speech recognition engine storage unit.
First voice recognition processor 170 is corresponding to utilizing the low-power processor of low-power operation, and by using the first speech recognition modeling to perform speech recognition.First voice recognition processor 170 can comprise the first voice recognition processing unit 110, and wherein, the first voice recognition processing unit 110 comprises the first pretreatment unit 111, first speech recognition modeling storage unit 112 and the first voice recognition unit 113.
Before the first voice recognition unit 113 performs speech recognition, the first pretreatment unit 111 can be modified to the voice signal inputted from microphone 400 and the voice signal revised be outputted to the first voice recognition unit 113.Optionally realize the first pretreatment unit 111 or omit the first pretreatment unit 111 according to implementation.
First speech recognition modeling storage unit 112 can store the first speech recognition modeling, and produce by speech recognition training or upgrade the first speech recognition modeling storage unit 112, wherein, the first speech recognition modeling comprises the various speech recognition algorithms for speech recognition.
According to various embodiments of the present invention, first speech recognition modeling can comprise first order speech recognition algorithm, wherein, first order speech recognition algorithm identifiable design comprises the first order voice of pre-set commands (such as, certain words or one or more single contamination).Such as, the first speech recognition modeling person's recognizer that can be language.
First voice recognition unit 113 is by using the first speech recognition modeling to identify voice.According to various embodiments of the present invention, the first voice recognition unit 113 identifiable design utilizes the first order voice in the first voice recognition processor 170 of low-power operation.Such as, the first voice recognition unit 113 identifiable design comprises the order of booking list contamination " hello, Gai Leshi ".
In addition, second voice recognition processor 180 can comprise the second voice recognition processing unit 220, controller 210 and audio frequency controller unit 230, second voice recognition processing unit 220 can comprise the second speech recognition modeling storage unit 222 and the second voice recognition unit 223.In the description, audio frequency controller unit can be called voice management unit.
Second voice recognition processor 180 can comprise controller 210, second voice recognition processing unit 220 and audio frequency controller unit 230.According to various embodiments of the present invention, second voice recognition processor 180 also can comprise the 3rd voice recognition processing unit, wherein, the 3rd voice recognition processing unit comprises the 3rd pretreatment unit, the 3rd speech recognition modeling storage unit and the 3rd voice recognition unit.Here, the second voice recognition processor 180 can utilize the power different from the power of the first voice recognition processor 170 to operate.
Controller 210 controls the first voice recognition processor 170 or/and the general operation (the signal control etc. such as, between speech recognition controlled, each element) of the second voice recognition processor 180.In addition, controller 210 can be connected to audio frequency controller unit 230 to receive phonetic entry/output signal.Controller 210 is by using application and program information and controlling the operation of the first voice recognition processing unit 110 and the second voice recognition processing unit 220 from the information that audio frequency controller unit 230 receives.According to embodiments of the invention, although be described in the second voice recognition processor 180 to comprise controller 210, but the present invention is not limited thereto, can the first voice recognition processor 170 comprise controller 210 or can with the first voice recognition processor 170 and the second voice recognition processor 180 phase Configuration Control Unit 210 independently.In addition, according to various embodiments of the present invention, the first voice recognition processor 170 is or/and the second voice recognition processor 180 can control each operation.
Second voice recognition processing unit 220 can comprise the second pretreatment unit 221, second speech recognition modeling storage unit 222 and the second voice recognition unit 223.
Before the second voice recognition unit 223 performs speech recognition, the second pretreatment unit 221 can revise the voice signal inputted from microphone 400, and the voice signal revised can be outputted to the second voice recognition unit 223.Optionally realize the second pretreatment unit 221 or the second pretreatment unit 221 can be omitted according to implementation.
Second speech recognition modeling storage unit 222 stores the second speech recognition modeling of the speech recognition being used for the second voice recognition unit 223.
According to various embodiments of the present invention, second speech recognition modeling can comprise second level speech recognition algorithm, wherein, second level speech recognition algorithm not only identifiable design can by the first order voice of the first speech recognition modeling identification, and also identifiable design comprises the second level voice of the order of a word.The comparable first speech recognition algorithm identification of second speech recognition algorithm is more ordered.In addition, produce by speech recognition training or upgrade the second speech recognition modeling.
Second voice recognition unit 223 is by using the second speech recognition modeling to identify second level voice.Second voice recognition unit 223 can perform than the more high performance speech recognition of the first voice recognition unit 113.Such as, the second voice recognition unit 223 identifiable design comprises the order of at least one word (such as, " broadcasting ", " stopping ", " time-out " etc.).
Audio frequency controller unit 230 is directly or indirectly connected to microphone 400 and loudspeaker 410 inputing or outputing with Managing speech signal.In addition, the voice signal exported from audio-frequency module 420 can be sent to the second pretreatment unit 221 by audio frequency controller unit 230.The I/O of the sound signal of the application of audio frequency controller unit 230 ALARA Principle or program, and determine whether from loudspeaker 410 output audio signal.
Fig. 3 illustrates the configuration of the first voice recognition processor according to various embodiment and the second voice recognition processor.
According to various embodiments of the present invention, electronic installation 101 can be realized audio-frequency module is removed and is included in the first voice recognition processor 170 and the second voice recognition processor 180.The element of electronic installation 101 can be run in the same manner as the description of Fig. 2.
According to Fig. 3, controller 210 receives the voice signal inputted from microphone 400 by audio frequency controller unit 230.Voice signal can be sent to loudspeaker 410 from microphone 400 received speech signal by audio frequency controller unit 230, therefore exports voice by loudspeaker 410.
Second voice recognition unit 223 is by using the first speech recognition modeling of the first voice recognition processor 170 to identify voice.In addition, the first voice recognition unit 113 and/or the second voice recognition unit 223 can perform speech recognition to identify the special sound of particular speaker.
Fig. 4 illustrates the configuration of the first voice recognition processor according to various embodiment and the second voice recognition processor.
According to various embodiments of the present invention, electronic installation can comprise the second voice recognition processor 180, and wherein, the second voice recognition processor 180 comprises two voice recognition processing unit.
Second voice recognition processor 180 can comprise the second voice recognition processing unit 220 and the 3rd voice recognition processing unit 240.Second speech recognition modeling of the second voice recognition processing unit 220 and the 3rd speech recognition modeling of the 3rd voice recognition processing unit 240 can comprise different speech recognition algorithms.3rd speech recognition modeling can comprise the third level speech recognition algorithm of the order for identifying multiple single contamination.Such as, third level voice can be that the phrase of the combination of multiple word (such as, " opening camera ") is or/and sentence.According to various embodiment, the second speech recognition modeling can be the model of cognition identical with first language model of cognition with a model in the 3rd speech recognition modeling.
3rd voice recognition processing unit 240 can comprise the 3rd pretreatment unit 241, the 3rd speech recognition modeling storage unit 242 and the 3rd voice recognition unit 243.
Before the 3rd voice recognition unit 243 performs speech recognition, the 3rd pretreatment unit 241 can be revised the voice signal from microphone 400 input and the voice signal revised is outputted to the 3rd voice recognition unit 243.Optionally implement the 3rd pretreatment unit 241 or the 3rd pretreatment unit 241 can be omitted according to implementation.
3rd speech recognition modeling storage unit 242 stores the 3rd speech recognition modeling of the speech recognition being used for the 3rd voice recognition unit 243.According to various embodiments of the present invention, the 3rd speech recognition modeling can comprise third level speech recognition algorithm, and wherein, third level speech recognition algorithm identifiable design comprises the phrase of multiple single contamination or/and the third level voice of sentence.Third level speech recognition algorithm identifiable design is more ordered than second level speech recognition algorithm.Such as, third level speech recognition algorithm can be the algorithm of natural-sounding recognizer and the order for the combination that identifies multiple word (such as, " opening camera ").
3rd voice recognition unit 243 is by using the 3rd speech recognition modeling to identify third level voice.
Fig. 5 illustrates the configuration of the first voice recognition processor according to various embodiment and the second voice recognition processor.
According to various embodiment, in electronic installation 101, the first voice recognition processor 170 can also comprise Audio Processing Unit 110-1, the voice signal inputted can be sent to Audio Processing Unit 150 from microphone 400.According to various embodiments of the present invention, the first voice recognition processor 170 can be used as audio-frequency module work.
The voice signal inputted from microphone 400 (that is, simulating signal) can be converted to digital signal and output digit signals by Audio Processing Unit 110-1, or performs the speech processes of such as automatic growth control (AGC).Voice signal by Audio Processing Unit 110-1 process is sent to the second voice recognition processing unit 220 by the audio frequency controller unit 230 of the second voice recognition processor 180 or by apply or program uses by the voice signal of Audio Processing Unit 110-1 process.
First voice recognition unit 113 is by using the first speech recognition modeling to identify voice.First speech recognition modeling can comprise first order speech recognition algorithm and can be for the model of cognition identifying phonetic entry or trained by user.
When application is performed, the second voice recognition unit 223 is by using the second speech recognition modeling being exclusively used in the application of execution to identify voice.Such as, the second speech recognition modeling can be word identification model or large vocabulary speech recognition modeling, wherein, and several words of word identification model identifiable design.
Fig. 6 illustrates the configuration of the first voice recognition processor, the second voice recognition processor and the 3rd voice recognition processor according to various embodiment.
According to various embodiments of the present invention, electronic installation 101 can comprise the first voice recognition processor and the second voice recognition processor 180, and external electronic can comprise the 3rd voice recognition processor 190.
First voice recognition processor 170 can comprise the first pretreatment unit 111, first speech recognition modeling storage unit 112 and the first voice recognition unit 113.
When receiving voice signal from microphone 400, first voice pretreatment unit 111 revise receive the first voice and by amendment the first voice transfer to the first voice recognition unit 113.
First speech recognition modeling storage unit 112 can store the first speech recognition modeling comprising first order speech recognition algorithm, wherein, and first order speech recognition algorithm identifiable design first order voice.
First voice recognition unit 113 is by using the first speech recognition modeling to identify the first voice and determining whether the first voice identified comprise the first order.When determining that the first voice comprise the first order, the first voice recognition unit 113 can by the second voice transfer of input to the 3rd voice recognition processor 190.In addition, when determining that the first voice do not comprise the first order, the first voice recognition unit 113 terminated speech identification.
Second voice recognition processor 180 can comprise controller 210, second pretreatment unit 221, second speech recognition modeling storage unit 222 and the second voice recognition unit 223.
Controller 210 controls the first voice recognition processor 170 or/and the general operation (the signal control etc. such as, between speech recognition controlled, each element) of the second voice recognition processor 180.According to various embodiments of the present invention, when receiving the first voice, controller 210 can by the first voice transfer to the second voice pretreatment unit 221.When the second voice recognition unit 223 receives the result of speech recognition, controller 210 can perform the operation corresponding to the result of speech recognition.
According to various embodiments of the present invention, although be described in the second voice recognition processor 180 to comprise controller 210, but the present invention is not limited thereto, and can the first voice recognition processor 170 comprise controller 210 or can with the first voice recognition processor 170 and the second voice recognition processor 180 Configuration Control Unit 210 separately.In addition, according to various embodiments of the present invention, the first voice recognition processor 170 is or/and the second voice recognition processor 180 can control each operation.
Before the second voice recognition unit 223 performs speech recognition, the second pretreatment unit 221 can be revised voice signal and the voice signal of amendment is outputted to the second voice recognition unit 223.Optionally realize the second pretreatment unit 221 or the second pretreatment unit 221 can be omitted according to implementation.
Second speech recognition modeling storage unit 222 can store the second speech recognition modeling comprising second level speech recognition algorithm, wherein, and the speech recognition algorithm identifiable design second level, second level voice.According to various embodiments of the present invention, second level voice can comprise first order voice.
Second voice recognition unit 223 is by using the second speech recognition modeling to identify the first voice and determining whether the first voice identified comprise the first order.When determining that the first voice comprise the first order, the second voice that the second voice recognition unit 223 identifiable design inputs also determine whether the second voice identified comprise the second order.When determining that the first voice do not comprise the first order, the second voice recognition unit 223 terminated speech identification.
In addition, when determining that the second voice comprise the second order, the result of speech recognition can be sent to controller 210 by the second voice recognition unit 223, and controller 210 can perform orders corresponding operation to second.When determining that the second voice do not comprise the second order, the second voice recognition unit 223 terminated speech identification.
3rd voice recognition processing unit 190 can comprise the 3rd pretreatment unit 310, the 3rd speech recognition modeling storage unit 320 and the 3rd voice recognition unit 330.
Before the 3rd voice recognition unit 330 performs speech recognition, the 3rd pretreatment unit 310 can be revised voice signal and the voice signal of amendment is outputted to the 3rd voice recognition unit 330.Optionally realize the 3rd pretreatment unit 310 or the 3rd pretreatment unit 310 can be omitted according to realization.
3rd speech recognition modeling storage unit 320 can store the 3rd speech recognition modeling comprising third level speech recognition algorithm, wherein, and third level speech recognition algorithm identifiable design third level voice.
3rd voice recognition unit 330 is by using the 3rd speech recognition modeling to identify the second voice and determining whether the second voice identified comprise the second order or/and the 3rd order.When determine the second voice comprise the second order or/and the 3rd order time, the result of speech recognition can be sent to the second voice recognition processor 180 by the 3rd voice recognition unit 330.When determine the second voice do not comprise the second order or/and the 3rd order time, the 3rd voice recognition unit 330 terminated speech identification.
After this, the second voice recognition processor 180 can perform and order or/and the 3rd orders corresponding operation to second.
According to various embodiments of the present invention, electronic installation can comprise at least one device in the first speech recognition equipment and the second speech recognition equipment, at least one device described obtains the first voice, wherein, when the first voice obtained by the first speech recognition equipment comprise predetermined command, extra the second voice identified are identified by external electronic, and when the first voice obtained by the second speech recognition equipment comprise predetermined command, identify extra the second voice identified, then perform associative operation based on the second voice identified.
Fig. 7 illustrates the configuration of the first voice recognition processor, the second voice recognition processor and the 3rd voice recognition processor according to various embodiment.
According to various embodiments of the present invention, electronic installation can comprise the first voice recognition processor 170 and the second voice recognition processor 180, and external electronic can comprise the 3rd voice recognition processor 190.
First voice recognition processor 170 can comprise the first pretreatment unit 111, first speech recognition modeling storage unit 112 and the first voice recognition unit 113.
When receiving voice signal from microphone 400, first pretreatment unit 111 revise receive the first voice and by amendment the first voice transfer to the first voice recognition unit 113.
First speech recognition modeling storage unit 112 can store the first speech recognition modeling comprising first order speech recognition algorithm, wherein, and first order speech recognition algorithm identifiable design first order voice.
First voice recognition unit 113 is by using the first speech recognition modeling to identify the first voice and determining whether the first voice identified comprise the first order.When determining that the first voice comprise the first order, the first voice recognition unit 113 can by the second voice transfer of input to the 3rd voice recognition processor 190.When determining that the first voice do not comprise the first order, the first voice recognition unit 113 can by the first voice transfer to the second voice recognition processor 180.
Second voice recognition processor 180 can comprise controller 210, second pretreatment unit 221, second speech recognition modeling storage unit 222 and the second voice recognition unit 223.
When receiving the first voice, controller 210 can by the first voice transfer to the second pretreatment unit 221.When receiving the result of speech recognition by the second voice recognition unit 223, controller 210 can perform the operation corresponding to the result of speech recognition.
Before the second voice recognition unit 223 performs speech recognition, the second pretreatment unit 221 can be revised voice signal and the voice signal of amendment is outputted to the second voice recognition unit 223.Optionally realize the second pretreatment unit 221 or the second pretreatment unit 221 can be omitted according to implementation.
Second speech recognition modeling storage unit 222 can store the second speech recognition modeling comprising second level speech recognition algorithm, wherein, and the speech recognition algorithm identifiable design second level, second level voice.
Second voice recognition unit 223 is by using the second speech recognition modeling to identify the first voice and determining whether the first voice identified comprise the first order.When determining that the first voice comprise the first order, the second voice that the second voice recognition unit 223 identifiable design inputs also determine whether the second voice identified comprise the second order.When determining that the first voice do not comprise the first order, the second voice recognition unit 223 terminated speech identification.
In addition, when determining that the second voice comprise the second order, the result of speech recognition can be sent to controller 210 by the second voice recognition unit 223, and controller 210 can perform orders corresponding operation to second.When determining that the second voice do not comprise the second order, the second voice recognition unit 223 terminated speech identification.
According to various embodiment, when determining that the first voice do not comprise the first order, the second voice recognition unit 223 can determine whether the first voice comprise the second order.When determining that the first voice comprise the second order, the result of speech recognition can be sent to controller 210 by the second voice recognition unit 223.
3rd voice recognition processing unit 190 can comprise the 3rd pretreatment unit 310, the 3rd speech recognition modeling storage unit 320 and the 3rd voice recognition unit 330.
Before the 3rd voice recognition unit 330 performs speech recognition, the 3rd pretreatment unit 310 can be revised voice signal and the voice signal of amendment is outputted to the 3rd voice recognition unit 330.Optionally realize the 3rd pretreatment unit 310 or the 3rd pretreatment unit 310 can be omitted according to implementation.
3rd speech recognition modeling storage unit 320 can store the 3rd speech recognition modeling comprising third level speech recognition algorithm, wherein, and third level speech recognition algorithm identifiable design the 3rd voice.
3rd voice recognition unit 330 is by using the 3rd speech recognition modeling to identify the second voice and determining whether the second voice identified comprise the second order or/and the 3rd order.When determine the second voice comprise the second order or/and the 3rd order time, the result of speech recognition can be sent to the second voice recognition processor 180 by the 3rd voice recognition unit 330.When determine the second voice do not comprise the second order or/and the 3rd order time, the 3rd voice recognition unit 330 terminated speech identification.
Fig. 8 illustrates the configuration of the pretreatment unit according to various embodiment.
Pretreatment unit 800 can comprise adaptive echo canceller (AEC), squelch (NS) unit 802, end point determination (EPD) unit 803, automatic growth control (AGC) unit 804 according to an embodiment of the invention.
Adaptive echo canceller 801 performs the operation removing echo from voice signal based on reference signal, wherein, from microphone 810 input speech signal.Such as, if when exporting sound (such as, call, the tinkle of bells, music player, camera etc.) application export voice signal when performing to the second voice recognition processor 180, then adaptive echo canceller 801 can remove echo and voice signal is transferred to voice recognition unit 820 from the voice signal of input, wherein, echo is inputted by the execution of application.
Noise suppression unit 802 performs the operation suppressing to come from the noise of the voice signal of input.
In fact the operation that end point determination unit 803 performs the terminal detecting voice is present in part in the voice signal of input to search voice.
Even if the transmission intensity of voice signal that automatic gain control unit 804 performs input is changed the operation of the good voice signal of also automatic reception.
Can not element be comprised so that with low-power operation in first pretreatment unit 111, in the second pretreatment unit 221, all elements can be comprised to improve the performance of speech recognition.But, be not limited thereto in an embodiment of the present invention, can comprise in every way or get rid of element.
According to various embodiments of the present invention, the first voice recognition processor 170 can be embodied as low-power processor.Even when the second voice recognition processor 180 is in idle pulley, the first voice recognition processor 170 can the input of waiting voice signal.Here, idle pulley indicates the state be not powered, wherein, the screen of electronic installation 101 be closed and only necessary element by supplying minimum electric power to operate.
When inputting voice from microphone 400, the first voice recognition unit 113 of the first voice recognition processor 170 identifies the voice of input.When the voice inputted comprise the order for activating the second voice recognition processor 180, the signal being used for activating the second voice recognition processor 180 is sent to controller 210 by the first voice recognition unit 113.After this, controller 210 is by activating the second voice recognition processing unit 220 to perform speech recognition.
Even when the second voice recognition processor 180 is in active state, controller 210 performs speech recognition by the first voice recognition processor 170.Now, controller 210 is by using application message and controlling the operation of the first voice recognition processor 170 from the information that audio frequency controller unit 230 receives or control the operation of the first voice recognition processing unit 110 and the second voice recognition processing unit 220.
According to the various embodiments with invention, when receiving voice, electronic installation 101 performs speech recognition by the first voice recognition processor 170, based on the audio treatment unit processed sound signal (such as, audio-frequency module, loudspeaker, audio frequency controller unit etc.) operation stop the speech recognition of the first voice recognition processor 170, and perform speech recognition by the second voice recognition processor 180.
According to various embodiments of the present invention, according to whether from loudspeaker output audio signal, can by from select in the processor of low-power operation and high-performance processor processor to perform speech recognition.
Such as, when the application or program for illustrating sound is performed, if be transfused to for the voice signal of speech recognition, then become echo from the sound shown in loudspeaker and flow into microphone, correspondingly, the voice signal distortion of input, and then perform speech recognition by high-performance processor.
Fig. 9 illustrates the process flow diagram being performed the process of speech recognition according to the controller of various embodiment by the first voice recognition processor or the second voice recognition processor.
When in step 900, voice are transfused to, controller 210 makes the first voice recognition processor 170 inactivation in step 910.When voice are not transfused to, controller 210 can enter step 930.Here, inactivation instruction stops powering to the first voice recognition processing unit 110 and stopping the operation of the speech recognition of the first voice recognition processing unit 110 in the first voice recognition processor 170.According to various embodiment, controller 210 controls audio frequency controller unit 230 to determine whether to export voice from loudspeaker 410.
The controller 210 having entered step 920 from step 910 performs speech recognition by the second voice recognition processing unit 220 of the second voice recognition processor 180.
In step 930, controller 210 makes the second voice recognition processing unit 220 of the second voice recognition processor 180 and the state inactivation of audio-frequency module 420.In other words, controller 210 stops powering to the second voice recognition processing unit 220 and audio-frequency module 420 and they being switched to idle condition.That is, controller 210 can make the speech recognition operation in the second voice recognition processing unit 220 and audio-frequency module 420 stop.
In step 940, controller 210 performs speech recognition by the first voice recognition processor 170.
Figure 10 illustrates the process flow diagram being performed the process of speech recognition according to the controller of various embodiment by the first voice recognition processor or the second voice recognition processor.
According to various embodiments of the present invention, in step 100, controller 210 determines whether voice are transfused to.Enter step 1010 when voice are transfused to Time Controller 210, and enter step 1020 when voice are not transfused to Time Controller.
In step 1010, controller 210 performs speech recognition by the second voice recognition processing unit 220.
In step 1020, controller 210 makes the second voice recognition processing unit 220 inactivation, and activates the first voice recognition processor 170 in step 1030 middle controller 210.According to various embodiments of the present invention, activation refers to by the state of the first voice recognition processor 170 being switched to the state that can perform speech recognition operation to the first voice recognition processor 170 power supply being in idle condition.In other words, the state that the first voice recognition processing unit 110 referring to the first voice recognition processor 170 can perform speech recognition operation is activated.
In step 1040, controller 210 performs speech recognition by the first voice recognition processor 170.
Figure 11 illustrates the process flow diagram being performed the process of speech recognition according to the controller of various embodiment by the first voice recognition processor or the second voice recognition processor.
According to various embodiments of the present invention, controller 210 determines whether the application of output audio signal is just performed.When the application of output audio signal is just performed, controller 210 enters step 1110, and when the application of output audio signal is not performed, controller 210 enters step 1120.Here, when the application of output audio signal is just performed, controller 210 can be determined to export sound by loudspeaker.
In step 1110, controller 210 performs speech recognition by the second voice recognition processor 220.
In step 1120, controller 210 makes the second voice recognition processing unit 220 inactivation, and in step 1130, controller 210 activates the first voice recognition processor 170.
In step 1140, controller 210 performs speech recognition by the first voice recognition processor 170 activated.
Figure 12 illustrates the process flow diagram being performed the process of speech recognition according to the controller of various embodiment by the first voice recognition processor or the second voice recognition processor.
According to various embodiments of the present invention, in step 1200, controller 210 determines whether audio-frequency module 420 is activated.When audio-frequency module 420 Time Controller 210 that is activated enters step 1210, and when audio-frequency module 420 Time Controller that is not activated enters step 1220.Here, the activation of audio-frequency module 420 refers to the state that audio-frequency module 420 works.
In step 1210, controller 210 performs speech recognition by the second voice recognition processor 220.
In step 1220, controller 210 makes the second voice recognition processing unit 220 inactivation, and in step 1230, controller 210 activates the first voice recognition processor 170.
In step 1240, controller 210 performs speech recognition by the first voice recognition processor 170.
Such as, when the voice of " hello, Gai Leshi " are pre the wake command for activating, if receive the voice of " hello, Gai Leshi " from microphone 400, then controller 210 can activate specific voice recognition processor.After this, controller 210 performs extra speech recognition by using the voice recognition processor activated, or stops or starting the operation of specific voice recognition processor.Voice can identify by the second voice recognition unit 220 of the first voice recognition unit 110 of the first voice recognition processor 170 or the second voice recognition processor 180.
In addition, when the application or program of reproducing music are performed, if become echo from the sound signal shown in loudspeaker 400 and flow into microphone, then the voice signal be input in microphone 400 can distortion.Substantially, the controller 210 being performed speech recognition by the first voice recognition processor 170 can determine whether by loudspeaker 410 output audio signal, and when illustrating sound signal by loudspeaker 410, controller 210 makes the first voice recognition processor 170 inactivation and activates the second voice recognition processor 220.According to various embodiments of the present invention, controller can determine whether by loudspeaker 410 output audio signal, to determine whether whether reproducing music application be activated in operation or audio-frequency module 420.
In addition, the second pretreatment unit 221 perform for suppress input voice distortion signal transacting (such as, AEC etc.) and by refine voice transfer to the second voice recognition unit 223.
Figure 13 illustrates the process being performed speech recognition by the first voice recognition processor, the second voice recognition processor and the 3rd voice recognition processor according to various embodiment.
In step 1300, the first voice recognition processor 170 and the second voice recognition processor 180 can receive the first voice from microphone 400.
In step 1301, the first voice recognition processor 170 identifies the first voice and determines whether the first voice comprise the first order.When the first voice comprise the first order, the first voice recognition processor 170 enters step 1302, and the first voice recognition processor 170 terminated speech identification when the first voice do not comprise the first order.
In step 1302, the first voice recognition processor 170 determines whether the second voice are received.When the second voice are received, the first voice recognition processor 170 enters step 1303, and the first voice recognition processor 170 terminated speech identification when the second voice are not received.
In step 1303, the first voice recognition processor 170 can by the second voice transfer of reception to the 3rd voice recognition processor 190, then terminated speech identification.Correspondingly, after receiving and identifying the second voice, the result of identification can be sent to the first voice recognition processor 170 or the second voice recognition processor 180 by the 3rd voice recognition processor 190, and the first voice recognition processor 170 or the second voice recognition processor 180 can perform the operation corresponding to recognition result.
In step 1304, the second voice recognition processor 180 identifies the first voice and determines whether the first voice comprise the first order.When the first voice comprise the first order, the second voice recognition processor 180 enters step 1305, and the second voice recognition processor 180 terminated speech identification when the first voice do not comprise the first order.
In step 1305, the second voice recognition processor 180 determines whether the second voice are received.When the second voice are received, the second voice recognition processor 180 enters step 1306, and the second voice recognition processor 180 terminated speech identification when the second voice are not received.
In step 1306, the second voice recognition processor 180 identifies the second voice received, and when the second voice comprise the second order, the second voice recognition processor 180 enters step 1307 and performs orders corresponding operation to second.
Use the method for electronic installation can comprise following operation: to obtain the first voice by least one device in the first speech recognition equipment and the second speech recognition equipment; The second voice additionally identified by external electronic identification when the first voice obtained by the first speech recognition equipment comprise predetermined command; Extra the second voice identified are identified when the first voice obtained by the second speech recognition equipment comprise predetermined command; Associative operation is performed based on the second voice identified.
Figure 14 illustrates the process being performed speech recognition by the first voice recognition processor, the second voice recognition processor and the 3rd voice recognition processor according to various embodiment.
In step 1400, the first voice recognition processor 170 receives the first voice from microphone 400.
In step 1401, the first voice recognition processor 170 identifies the first voice and determines whether the first voice comprise the first order.When the first voice comprise the first order, the first voice recognition processor 170 enters step 1402, and when the first voice do not comprise the first order, the first voice recognition processor terminated speech identification.
In step 1402, the first voice recognition processor 170 determines whether the second voice are received.When the second voice are received, the first voice recognition processor 170 enters step 1403, and when the second voice are not received, the first voice recognition processor 170 terminated speech identification.
In step 1403, the first voice recognition processor 170 can by the second voice transfer of reception to the 3rd voice recognition processor 190, then terminated speech identification.Correspondingly, after receiving and identifying the second voice, the result of identification can be sent to the first voice recognition processor 170 or the second voice recognition processor 180 by the 3rd voice recognition processor 190, and the first voice recognition processor 170 or the second voice recognition processor 180 can perform the operation corresponding to recognition result.
In step 1404, the second voice recognition processor 180 identifies the first voice and determines whether the first voice comprise the first order.When the first voice comprise the first order, the second voice recognition processor 180 enters step 1405, and when the first voice do not comprise the first order, the second voice recognition processor 180 terminated speech identification.
In step 1405, the second voice recognition processor 180 determines whether the second voice are received.When the second voice are received, the second voice recognition processor 180 enters step 1406, and when the second voice are not received, the second voice recognition processor 180 terminated speech identification.
In step 1406, the second voice recognition processor 180 identifies the second voice received, and when the second voice comprise the second order, the second voice recognition processor 180 enters step 1407 and performs orders corresponding operation to second.
Figure 15 illustrates the process being performed speech recognition by the first voice recognition processor, the second voice recognition processor and the 3rd voice recognition processor according to various embodiment.
In step 1500, the first voice recognition processor 170 can perform application-specific.
In step 1501, the first voice recognition processor 170 can receive the first voice from microphone 400.
In step 1502, the first voice recognition processor 170 can determine whether can perform speech recognition for the application performed.When performing speech recognition, the first voice recognition processor 170 can enter step 1503, and when performing speech recognition, the first voice recognition processor 170 enters step 1507.
In step 1503, the first voice recognition processor 170 identifies the first voice and determines whether the first voice comprise the first order.When the first voice comprise the first order, the first voice recognition processor 170 enters step 1504, and when the first voice do not comprise the first order, the first voice recognition processor 170 enters step 1505.
In step 1504, when the second voice are received, the first voice recognition processor 170 can by the second voice transfer of reception to the 3rd voice recognition processor 190.
In step 1505, the first voice recognition processor 170 identifies the first voice and determines whether the first voice comprise the 3rd order.When the first voice comprise the 3rd order, the first voice recognition processor 170 enters step 1506, and when the first voice do not comprise the 3rd order, the first voice recognition processor 170 terminated speech identification.
In step 1506, the first voice recognition processor 170 can perform orders corresponding operation to the 3rd.
In step 1507, the second voice recognition processor 180 can perform speech recognition to the application run.
In step 1508, the second voice recognition processor 180 identifies the first voice and determines whether the first voice comprise the first order.When the first voice comprise the first order, the second voice recognition processor 180 enters step 1509, and when the first voice do not comprise the first order, the second voice recognition processor 180 performs step 1505 and step 1506 in a single stage.
In step 1509, when the second voice are received, second voice recognition processor 180 can determine whether the second voice comprise the second order, and when the second voice comprise the second order, the second voice recognition processor 180 performs and orders corresponding operation to second.
Figure 16 illustrates the process of being upgraded by speech recognition modeling by the 3rd voice recognition processor according to various embodiment.
In step 1600, the 3rd voice recognition processor 190 identifies the second voice.
In step 1601, the 3rd voice recognition processor 190 can determine whether there is the order relevant to the second voice in pre-set commands.When there is the order relevant to the second voice, the 3rd voice recognition processor 190 can enter step 1602, and when there is not the order relevant to the second voice, the 3rd voice recognition processor 190 enters step 1603.Such as, when the second voice identified are " beginnings ", the 3rd voice recognition processor 190 can determine whether there is the order relevant to " beginning " or/and be similar to the order of " beginning ".
In step 1602, the 3rd voice recognition processor 190 upgrades the second speech recognition modeling storage unit 222 by the corresponding command that the second voice made to identify are corresponding.
When the order of the reproduction for starting video be configured to can " startup " in the video player application function of rendered video time, if determine relevant or/and when similar order is " startup " to " beginning " identified, by making, " beginning " of identification is corresponding with " startup " upgrades the second speech recognition modeling storage unit 222 to the 3rd voice recognition processor 190.In other words, except " startup ", the 3rd voice recognition processor 190 also can be able to increase in the order of the reproduction for starting video in the video player application function of reproducing video and store " beginning ".
In step 1603, when there is not the order relevant to the second voice, the 3rd voice recognition processor 190 determines whether there is the apparatus function relevant to the second voice.When there is the apparatus function corresponding to the second voice, the 3rd voice recognition processor 190 enters step 1604, and when there is not the apparatus function relevant to the second voice, the 3rd voice recognition processor 190 stops order renewal rewards theory.Such as, when video player application is just being performed and the second voice are corresponding to " stopping ", the 3rd voice recognition processor 190 can determine whether there is the video player function relevant to " stopping ".
In step 1604, by making, corresponding apparatus function is corresponding with the second voice of identification upgrades the second speech recognition modeling storage unit 222 to the 3rd voice recognition processor 190.Such as, when " reproducing when the video player function relevant to " stopping " and stop ", " stopping " can configuring and be stored as the order for performing " reproduce and stop " function by the 3rd voice recognition processor 190.
According to various embodiment, the first voice recognition processor, the second voice recognition processor and the 3rd voice recognition processor even predetermined application be just performed or/and electronic installation be in idle pulley state under also can perform speech recognition.In order to reduce stand-by power consumption, first voice recognition processor, the second voice recognition processor and the 3rd voice recognition processor only can identify that wake command (such as in stand-by mode, " hello, Gai Leshi "), but all orders of identifiable design under the pattern of non-standby pattern.
According to various embodiment, when receiving " hello; Gai Leshi " while being performed in predetermined application, first voice recognition processor 170 and/or the second voice recognition processor 180 can perform application, wherein, described application can perform natural language speech identification and also identify " hello, Gai Leshi " that receive.After this, when receiving " opening camera ", the first voice recognition processor 170 " can be opened camera " and be sent to the 3rd voice recognition processor 190.When receiving the result of identification from the 3rd voice recognition processor 190, the first voice recognition processor 170 can perform camera applications according to recognition result.In addition, the second voice recognition processor 180 identifiable design " opening camera " of receiving perform application.
According to various embodiment, when while being performed in music application, the second voice recognition processor receives " hello; Gai Leshi ", first voice recognition processor 170 and/or the second voice recognition processor 180 can perform application, wherein, described application can perform natural language speech identification and also identify " hello, Gai Leshi " that receive.After this, when receiving " opening camera ", the first voice recognition processor 170 " can be opened camera " and be sent to the 3rd voice recognition processor 190.When receiving the result of identification from the 3rd voice recognition processor 190, the first voice recognition processor 170 can perform camera applications according to recognition result.In addition, the second voice recognition processor 180 identifiable design " opening camera " of receiving perform camera applications.
When being designated as the order such as " broadcasting ", " time-out ", " next one " controlling music application and being transfused to, the second voice recognition processor 180 identifiable design inputs and performs the function of relevant music application.
Figure 17 is the block diagram 1700 of the electronic installation 1701 according to various embodiment.
According to various embodiments of the present invention, electronic installation 1701 can all or part of in configuration example electronic installation as shown in Figure 1 101.With reference to Figure 17, electronic installation 1701 can comprise instruction application processor (AP) 1701, communication module 1720, subscriber identification module (SIM) block 1724, storer 1730, sensor assembly 1740, input media 1750, display 1760, interface 1770, audio-frequency module 1780, camera model 1791, power management module 1795, battery 1796, indicator 1797 and motor 1798.
Multiple hardware or the component software of AP1710 by driving operating system or application program to be operatively connected to AP1710 connection, process comprises various types of data of multi-medium data and performs calculating.AP1710 can be realized by such as SOC (system on a chip) (SoC).According to embodiment, AP1710 also can comprise Graphics Processing Unit (GPU) (not shown).
Communication module 1720 (such as, communication interface 160) by network at electronic installation 1701 (such as, electronic installation 101) and other electronic installation (such as, electronic installation 104 or server 106) being connected to electronic installation 1701 between communication under perform data sending/receiving.According to embodiment, communication module 1720 can comprise cellular module 1721, Wi-Fi module 1723, BT module 1725, GPS module 1727, NFC module 1728 and radio frequency (RF) module 1729.
Cellular module 1721 provides audio call, video call, text service, Internet service etc. by communication network (such as, LTE, LTE-A, CDMA, WCDMA, UMTS, WiBro, GSM etc.).In addition, cellular module 1721 can use subscriber identification module (such as, SIM card 1724) distinguish and authentication communication network in electronic installation.According to embodiment, cellular module 1721 can perform at least some function in the function that can be provided by AP1710.Such as, cellular module 1721 can perform at least some function in multimedia control function.
According to embodiment, cellular module 1721 can comprise communication processor (CP).In addition, cellular module 1721 can be realized by such as SoC.Although such as cellular module 1721 (such as, communication processor), storer 1730 and the element of power management module 1795 be shown as and AP1710 phase in Figure 17 independent, but according to an embodiment, AP1710 can be implemented as at least some element (such as, cellular module 1710) comprised in said elements.
According to embodiment, AP1710 or cellular module 1721 are (such as, communication processor) can also process from least one order received in nonvolatile memory and other element or Data import the order or data that load to volatile memory, wherein, other element described is connected at least one in AP1710 and cellular module 1721.In addition, the data received from least one element in other element or the data created by least one element in other element can store in the nonvolatile memory by AP1710 or cellular module 1721.
Each module in Wi-Fi module 1723, BT module 1725, GPS module 1727 and NFC module 1728 can be comprised such as the treatment of the processor of the data that be send/receive by corresponding module.Although cellular module 1721, Wi-Fi module 1723, BT module 1725, GPS module 1727 and NFC module 1728 are shown as independent module in fig. 17, but at least some in cellular module 1721, Wi-Fi module 1723, BT module 1725, GPS module 1727 and NFC module 1728 (such as, two or more) module can be included in an integrated chip (IC) or an IC encapsulation.Such as, at least some processor (such as, corresponding to cellular module 1721 communication processor and the Wi-Fi processor corresponding with Wi-Fi module 1723) in the processor corresponding with NFC module 1728 to cellular module 1721, Wi-Fi module 1723, BT module 1725, GPS module 1727 can be implemented as a SoC.
RF module 1729 can send/receive data (such as, RF signal).Although not shown, RF module 1729 can comprise such as transceiver, power amplifier module (PAM), frequency filter, low noise amplifier (LNA) etc.In addition, RF module 1729 also can comprise and such as send/receive electromagnetic assembly (such as, conductor, wire etc.) in wireless communications in free space.Although cellular module 1721, Wi-Fi module 1723, BT module 1725, GPS module 1727 and NFC module 1728 are shown as a shared RF module 1729 in fig. 17, at least one module in cellular module 1721, Wi-Fi module 1723, BT module 1725, GPS module 1727 and NFC module 1728 send/receive RF signal by independent RF module.
SIM card 1724 can be the card comprising subscriber identification module, and can be inserted in the slot formed in the specific part of electronic installation.SIM card 1724 can comprise unique identifying information (such as, Integrated Circuit Card Identity symbol (ICCID)) or user profile (such as, IMSI International Mobile Subscriber Identity (IMSI)).
Storer 1730 (such as, storer 130) can comprise internal storage 1732 or external memory storage 1734.Internal storage 1732 can comprise volatile memory (such as, dynamic RAM (DRAM), static RAM (SRAM) (SRAM), synchronous dynamic ram (SDRAM) etc.) and volatile memory (such as, disposable programmable read only memory (OTPROM), programming ROM (PROM), electronically erasable programmable rom (EPROM), electric erazable programmable ROM (EEPROM), mask ROM, flash ROM, nand flash memory, NOR flash memory etc.).
According to embodiment, internal storage 1732 can be solid-state drive (SSD).External memory storage 1734 also can comprise flash drive (such as compact flash (CF), secure digital (SD), miniature secure digital (Micro-SD), mini secure digital (Mini-SD), extreme digital (xD), memory stick etc.).External memory storage 1734 is functionally connected to electronic installation 1701 by various interface.According to embodiment, electronic installation 1701 also can comprise the memory storage (or storage medium) of such as hard disk drive.
Sensor assembly 1740 can the mode of operation of measure physical quantities or detection. electronics 1701, and the information measuring or detect can be converted to electric signal.Sensor assembly 1740 can comprise at least one sensor in such as following item: gesture sensor 1740A, gyro sensor 1740B, barometric pressure sensor 1740C, magnetometric sensor 1740D, acceleration transducer 1740E, grip sensor 1740F, proximity transducer 1740G, color sensor 1740H (such as, red, green and blue (RGB) sensor), biology sensor 1740I, temperature/humidity sensor 1740J, illuminance transducer 1740K and ultraviolet (UV) sensor 1740M.Extraly or alternatively, sensor assembly 1740 can comprise such as Electronic Nose sensor (not shown), electromyogram graphy (EMG) sensor (not shown), electroencephalogram (EEG) sensor (not shown), cardiogram (ECG) sensor (not shown), infrared (IR) sensor (not shown), iris sensor (not shown), fingerprint sensor (not shown) etc.Sensor assembly 1740 also can comprise the control circuit of at least one sensor for controlling to be included in this.
Input media 1750 can comprise touch panel 1752, (numeral) sensor 1754, button 1756 or ultrasonic input media 1758.Touch panel 1752 identifiable design inputs with the touch of at least one type in Types Below: such as, capacitor type, resistor-type, infrared type and ultrasonic-type.Touch panel 1752 also can comprise control circuit.Touch panel 1752 also can comprise tactile layer.In such example, touch panel 1752 can provide tactile response to user.
The same or analogous method of method that inputs with the touch receiving user can be used or use independent identification plate to realize (numeral) sensor 1754.Button 1756 can comprise such as physical button, optics button or keypad.Ultrasonic input media 1758 senses by the microphone (such as, microphone 1788) of electronic installation 1701 ultrasonic signal of sound wave the device of identification data that are produced by input tool, and can perform wireless identification.According to embodiment of the present disclosure, electronic installation 1701 also can use communication module 1720 to receive user from the external device (ED) be connected with electronic installation 1701 (such as, computing machine or server) and input.
Display 1760 (such as, display 150) can comprise panel 1762, holographic imaging apparatus 1764 and projector 1766.Panel 1762 can be such as liquid crystal display (LCD), active-matrix Organic Light Emitting Diode (AM-OLED) etc.Panel 1762 can be implemented as such as head dummy, transparent or wearable.Panel 1762 and touch panel 1752 can by together be configured to individual module.Holographic imaging apparatus 1764 illustrates stereo-picture in atmosphere by making the interference of using up.Projector 1766 can project light onto on screen to show image.Such as, screen can be positioned at electronic installation 1701 inside or outside.According to embodiment of the present disclosure, display 1760 also can comprise the control circuit for control panel 1762, holographic imaging apparatus 1764 or projector 1766.
Interface 1770 can comprise such as, high-definition media interface (HDMI) 1772, USB (universal serial bus) (USB) 1774, optical interface 1776 or microminiature (D-sub) 1778.Interface 1770 can be included in the communication interface 160 such as shown in Fig. 1.Extraly or alternatively, interface 1770 can comprise such as mobile high definition and connect (MHL) interface, secure digital (SD) card/multimedia card (MMC) interface or Infrared Data Association (IrDA) standard interface.
Audio-frequency module 1780 can carry out bi-directional conversion to sound and electric signal.At least some element of audio-frequency module 1780 can be included in the input/output interface 140 such as shown in Fig. 1.Audio-frequency module 1780 can process the acoustic information inputed or outputed by such as loudspeaker 1782, receiver 1784, earphone 1786, microphone 1788 etc.
Camera model 1791 is the devices can taking rest image or video.According to embodiment, camera model 1791 can comprise one or more imageing sensor (such as, front sensors or rearmounted sensor), camera lens (not shown), image-signal processor (ISP) (not shown) or flashlamp be (not shown, such as, LED or xenon lamp).
The electric power of power management module 1795 ALARA Principle electronic installation 1701.Although not shown, power management module 1795 can comprise such as power management integrated circuit (PMIC), charge integrated circuit (IC) or battery or voltameter.
PMIC can be installed in such as integrated circuit or SoC semiconductor.Charging method can be divided into wired charging method and wireless charging method.Charging IC can charge to battery and carry out overvoltage protection or overcurrent protection to charger.According to embodiment, charging IC can comprise the charging IC at least one method in wireless charging method and wired charging method.The example of wireless charging can comprise magnetic resonance charging, magnetic induction charging and electromagnetism charging, and can be the additional circuit of wireless charging increase such as toroid winding, resonant circuit and rectifier.
Battery electric quantity table can measure the dump energy of such as battery, charging voltage and electric current or temperature.Battery 1796 can store or produce electric power and by use store or produce electric power power to electronic installation 1701.Battery 1796 can comprise such as rechargeable battery or solar cell.
Indicator 1791 can the particular state, starting state, message status, charged state etc. of a part (such as, AP1710) of display electronics assemblies 1701 or electronic installation 1701.Motor 1798 can convert the electrical signal to mechanical vibration.Although not shown, electronic installation 1701 can comprise the treating apparatus (such as, GPU) being used to indicate mobile TV.The standard that treating apparatus can play (DMB) according to digital multimedia, digital video plays (DVB), Media Stream etc. being used to indicate mobile TV carrys out processing media data.
The said modules of electronic installation according to various embodiments of the present invention can be formed by one or more assembly, can change the title of corresponding element according to the type of electronic installation.One or more assembly in aforementioned components can be comprised according to electronic installation of the present invention or also can comprise other additional assemblies, or some assemblies in aforementioned components can be omitted.In addition, some assemblies in the assembly of electronic installation according to various embodiments of the present invention can be combined to form single entity, and therefore can perform the function of the respective element before combination equivalently.
The term " module " used in various embodiments of the present invention can indicate the unit of one or more combination such as comprising hardware, software and firmware." module " can exchange with the term of such as unit, logic, logical block, assembly or circuit." module " can be the minimum unit of a part for integrated package or integrated package." module " can be the minimum unit performing one or more function or part of functions.Mechanically or in electricity can realize " module ".Such as, " module " according to various embodiments of the present invention can comprise for application specific integrated circuit (ASIC) chip, field programmable gate array (FPGA) and the programmable logic device that perform known operation or after this will be developed out.
According to various embodiment, device according to various embodiments of the present invention (such as, module and function thereof) or method (such as, operate) at least some can be implemented as the computer-readable recording medium of the storage instruction of the form of such as programming module.When one or more processor (such as, processor 210) fill order, one or more processor described can perform and order corresponding function.Computer-readable recording medium can be such as storer 130.At least some module in (such as, performing) programming module can be realized by such as processor 210.Module, program, routine, instruction set or the process that can such as comprise at least partially for performing at least one function of programming module.
Computer-readable recording medium can comprise magnetic medium (such as hard disk, floppy disk and tape), optical medium (such as compact disk ROM (read-only memory) (CD-ROM) and digital universal disc (DVD)), magnet-optical medium (such as floptical) and be specially configured as storing and the hard disk drive (such as, ROM (read-only memory) (ROM), random access storage device (RAM) and flash memory) of executive routine order.In addition, programmed instruction can comprise by using the higher-level language code that interpreter performs in a computer and the machine code made by compiler.Aforementioned hard disk drive can be configured to as one or more software module, to perform the operation of various embodiment of the present invention, vice versa.
At least one element in the element of description can be comprised according to module of the present invention or programming module, some element can be omitted or extra element can be comprised.The operation performed by module according to various embodiments of the present invention, programming module or other element can by order, parallel, repeat or be performed in the mode inspired.In addition, maybe can omit certain operations with different orders execution certain operations and maybe can increase other operation.
According to various embodiment, provide the storage medium storing order wherein.Order is configured to allow one or more processor to perform one or more operation when order is performed.One or more operation described can comprise following operation: obtain the first voice by least one device in the first speech recognition equipment and the second speech recognition equipment; The second voice additionally identified by external electronic identification when the first voice obtained by the first speech recognition equipment comprise predetermined command; Extra the second voice identified are identified when the first voice obtained by the second speech recognition equipment comprise predetermined command; Associative operation is performed based on the second voice identified.
According to various embodiment, provide the storage medium storing order wherein.Described order is configured to allow one or more processor to perform one or more operation when order is performed.One or more operation described can comprise following operation: perform predetermined application; Be application acquisition first voice by least one device in the first speech recognition equipment and the second speech recognition equipment; When the first voice obtained by the first speech recognition equipment comprise predetermined command, the second voice additionally identified by external electronic identification; When the first voice obtained by the second speech recognition equipment comprise predetermined command, the second voice additionally identified by external electronic identification.
Disclosed in instructions and service, embodiments of the invention are only to easily describe technical theme of the present invention and the particular instance helping to understand the present invention and propose.Therefore, except the embodiment disclosed herein, the form of all modifications that the scope of various embodiment of the present invention should be understood to include the technical conceive based on various embodiment of the present invention and describe or amendment.

Claims (18)

1. use a method for electronic installation, described method comprises:
The first voice are obtained by least one device in the first speech recognition equipment and the second speech recognition equipment;
When the first voice obtained by the first speech recognition equipment comprise predetermined command, identify extra the second voice identified by external electronic;
When the first voice obtained by the second speech recognition equipment comprise predetermined command, identify extra the second voice identified;
Associative operation is performed based on the second voice identified.
2. the method for claim 1, also comprises: perform associative operation based on the second voice by external electronic identification.
3. the method for claim 1, also comprises:
When the first voice obtained by the first speech recognition equipment do not comprise described predetermined command, obtain the first voice by the second speech recognition equipment;
When the first voice obtained by the second speech recognition equipment comprise described predetermined command, identify extra the second voice identified;
Associative operation is performed based on the second voice identified.
4. method as claimed in claim 3, also comprises:
When for the recognition failures of the second voice obtained by the second speech recognition equipment, by the 3rd speech recognition equipment identification second voice;
Associative operation is performed based on the second voice by the 3rd speech recognition equipment identification.
5. use a method for electronic installation, described method comprises:
Perform predetermined application;
Come for application acquisition first voice by least one device in the first speech recognition equipment and the second speech recognition equipment;
When the first voice obtained by the first speech recognition equipment comprise predetermined command, identify extra the second voice identified by external electronic;
When the first voice obtained by the second speech recognition equipment comprise predetermined command, identify extra the second voice identified by external electronic.
6. but method as claimed in claim 5, also comprises: do not comprise described predetermined command when the second voice obtained by the second speech recognition equipment when comprising another order, perform associative operation based on another order described.
7. method as claimed in claim 6, also comprises:
By the 3rd speech recognition equipment identification second voice;
When the order relevant to the second voice is included in default command set, upgrade command set based on the second voice.
8. method as claimed in claim 7, also comprises: when the order relevant to the second voice is not included in command set, in command set, upgrade the order relevant to the second voice.
9. an electronic installation, comprising:
At least one device in first speech recognition equipment and the second speech recognition equipment,
Wherein, the second voice additionally identified when the first voice obtained by the first speech recognition equipment comprise predetermined command are identified by external electronic, when the first voice obtained by the second speech recognition equipment comprise predetermined command, second voice of extra identification are identified, and then associative operation is performed based on the second voice identified.
10. electronic installation as claimed in claim 9, wherein, at least one device in the first speech recognition equipment and the second speech recognition equipment performs associative operation based on the second voice by external electronic identification.
11. electronic installations as claimed in claim 9, wherein, when the first voice obtained by the first speech recognition equipment do not comprise described predetermined command, second speech recognition equipment obtains the first voice, and when the first voice obtained by the second speech recognition equipment comprise predetermined command, the second voice that second speech recognition equipment identification additionally identifies, then perform associative operation based on the second voice identified.
12. electronic installations as claimed in claim 11, wherein, when for the recognition failures of the second voice obtained by the second speech recognition equipment, the second voice are identified by the 3rd speech recognition equipment, and associative operation is performed based on the second voice by the 3rd speech recognition equipment identification.
13. 1 kinds of electronic installations, comprising:
At least one device in first speech recognition equipment and the second speech recognition equipment, for when predetermined application is performed being described predetermined application acquisition first voice,
Wherein, when the first voice obtained by the first speech recognition equipment comprise predetermined command, second voice of extra identification are identified by external electronic, when the first voice obtained by the second speech recognition equipment comprise predetermined command, extra the second voice identified are identified by external electronic.
14. electronic installations as claimed in claim 13, wherein, when by second speech recognition equipment obtain the first voice do not comprise described predetermined command but comprise another order time, associative operation is performed based on another order described.
15. electronic installations as claimed in claim 14, wherein, the 3rd speech recognition equipment identification second voice, and when the order relevant to the second voice is included in default command set, command set is updated based on the second voice.
16. electronic installations as claimed in claim 15, wherein, when the order relevant to the second voice is not included in command set, the order relevant to the second voice is updated in command set.
The computer-readable recording medium of 17. 1 kinds of memory commands, described computer-readable recording medium has the program for executable operations stored therein, and described operation comprises:
The first voice are obtained by least one device in the first speech recognition equipment and the second speech recognition equipment;
When the first voice obtained by the first speech recognition equipment comprise predetermined command, identify extra the second voice identified by external electronic;
When the first voice obtained by the second speech recognition equipment comprise predetermined command, identify extra the second voice identified; And
Associative operation is performed based on the second voice identified.
18. 1 kinds of computer-readable recording mediums for executable operations, described operation comprises:
Perform predetermined application;
Come for application acquisition first voice by least one device in the first speech recognition equipment and the second speech recognition equipment;
When the first voice obtained by the first speech recognition equipment comprise predetermined command, identify extra the second voice identified by external electronic;
When the first voice obtained by the second speech recognition equipment comprise predetermined command, identify extra the second voice identified by external electronic.
CN201480047495.1A 2013-08-26 2014-08-26 Electronic device and method for speech recognition Active CN105493180B (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
KR20130101411 2013-08-26
KR10-2013-0101411 2013-08-26
PCT/KR2014/007951 WO2015030474A1 (en) 2013-08-26 2014-08-26 Electronic device and method for voice recognition

Publications (2)

Publication Number Publication Date
CN105493180A true CN105493180A (en) 2016-04-13
CN105493180B CN105493180B (en) 2019-08-30

Family

ID=52586943

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201480047495.1A Active CN105493180B (en) 2013-08-26 2014-08-26 Electronic device and method for speech recognition

Country Status (5)

Country Link
US (3) US10192557B2 (en)
EP (1) EP3040985B1 (en)
KR (1) KR102394485B1 (en)
CN (1) CN105493180B (en)
WO (1) WO2015030474A1 (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107590096A (en) * 2017-08-31 2018-01-16 联想(北京)有限公司 Method and processor for processor in electronic equipment
CN110223696A (en) * 2019-05-22 2019-09-10 平安科技（深圳）有限公司 A kind of acquisition method of voice signal, device and terminal device
CN110427097A (en) * 2019-06-18 2019-11-08 华为技术有限公司 Voice data processing method, apparatus and system
WO2020057467A1 (en) * 2018-09-20 2020-03-26 青岛海信电器股份有限公司 Information processing apparatus, information processing system and video apparatus
CN111199735A (en) * 2018-11-16 2020-05-26 阿尔派株式会社 Vehicle-mounted device and voice recognition method
CN112334977A (en) * 2018-08-14 2021-02-05 华为技术有限公司 Voice recognition method, wearable device and system

Families Citing this family (122)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8677377B2 (en) 2005-09-08 2014-03-18 Apple Inc. Method and apparatus for building an intelligent automated assistant
US9318108B2 (en) 2010-01-18 2016-04-19 Apple Inc. Intelligent automated assistant
US8977255B2 (en) 2007-04-03 2015-03-10 Apple Inc. Method and system for operating a multi-function portable electronic device using voice-activation
US8676904B2 (en) 2008-10-02 2014-03-18 Apple Inc. Electronic devices with voice command and contextual data processing capabilities
US20120311585A1 (en) 2011-06-03 2012-12-06 Apple Inc. Organizing task items that represent tasks to perform
US10276170B2 (en) 2010-01-18 2019-04-30 Apple Inc. Intelligent automated assistant
US10417037B2 (en) 2012-05-15 2019-09-17 Apple Inc. Systems and methods for integrating third party services with a digital assistant
BR112015018905B1 (en) 2013-02-07 2022-02-22 Apple Inc Voice activation feature operation method, computer readable storage media and electronic device
US10652394B2 (en) 2013-03-14 2020-05-12 Apple Inc. System and method for processing voicemail
US10748529B1 (en) 2013-03-15 2020-08-18 Apple Inc. Voice activated device for use with a voice-based digital assistant
US10176167B2 (en) 2013-06-09 2019-01-08 Apple Inc. System and method for inferring user intent from speech inputs
KR102394485B1 (en) * 2013-08-26 2022-05-06 삼성전자주식회사 Electronic device and method for voice recognition
KR102179506B1 (en) * 2013-12-23 2020-11-17 삼성전자 주식회사 Electronic apparatus and control method thereof
US9715875B2 (en) 2014-05-30 2017-07-25 Apple Inc. Reducing the need for manual start/end-pointing and trigger phrases
EP3149728B1 (en) 2014-05-30 2019-01-16 Apple Inc. Multi-command single utterance input method
US10170123B2 (en) 2014-05-30 2019-01-01 Apple Inc. Intelligent assistant for home automation
KR102208477B1 (en) 2014-06-30 2021-01-27 삼성전자주식회사 Operating Method For Microphones and Electronic Device supporting the same
US9338493B2 (en) 2014-06-30 2016-05-10 Apple Inc. Intelligent automated assistant for TV user interactions
FR3030177B1 (en) * 2014-12-16 2016-12-30 Stmicroelectronics Rousset ELECTRONIC DEVICE COMPRISING A WAKE MODULE OF AN ELECTRONIC APPARATUS DISTINCT FROM A PROCESSING HEART
US9721566B2 (en) 2015-03-08 2017-08-01 Apple Inc. Competing devices responding to voice triggers
US9886953B2 (en) 2015-03-08 2018-02-06 Apple Inc. Virtual assistant activation
US10460227B2 (en) 2015-05-15 2019-10-29 Apple Inc. Virtual assistant in a communication session
US10200824B2 (en) 2015-05-27 2019-02-05 Apple Inc. Systems and methods for proactively identifying and surfacing relevant content on a touch-sensitive device
US20160378747A1 (en) 2015-06-29 2016-12-29 Apple Inc. Virtual assistant for media playback
US10331312B2 (en) 2015-09-08 2019-06-25 Apple Inc. Intelligent automated assistant in a media environment
US10747498B2 (en) 2015-09-08 2020-08-18 Apple Inc. Zero latency digital assistant
US10740384B2 (en) 2015-09-08 2020-08-11 Apple Inc. Intelligent automated assistant for media search and playback
US10671428B2 (en) 2015-09-08 2020-06-02 Apple Inc. Distributed personal assistant
US9691378B1 (en) * 2015-11-05 2017-06-27 Amazon Technologies, Inc. Methods and devices for selectively ignoring captured audio data
US10691473B2 (en) 2015-11-06 2020-06-23 Apple Inc. Intelligent automated assistant in a messaging environment
US10956666B2 (en) 2015-11-09 2021-03-23 Apple Inc. Unconventional virtual assistant interactions
US10223066B2 (en) 2015-12-23 2019-03-05 Apple Inc. Proactive assistance based on dialog communication between devices
US10074364B1 (en) * 2016-02-02 2018-09-11 Amazon Technologies, Inc. Sound profile generation based on speech recognition results exceeding a threshold
US20170330566A1 (en) * 2016-05-13 2017-11-16 Bose Corporation Distributed Volume Control for Speech Recognition
KR20170136759A (en) * 2016-06-02 2017-12-12 엘지전자 주식회사 Home automation system and method for controlling the same
US10586535B2 (en) 2016-06-10 2020-03-10 Apple Inc. Intelligent digital assistant in a multi-tasking environment
DK179415B1 (en) 2016-06-11 2018-06-14 Apple Inc Intelligent device arbitration and control
DK201670540A1 (en) 2016-06-11 2018-01-08 Apple Inc Application integration with a digital assistant
US10931999B1 (en) * 2016-06-27 2021-02-23 Amazon Technologies, Inc. Systems and methods for routing content to an associated output device
US10271093B1 (en) * 2016-06-27 2019-04-23 Amazon Technologies, Inc. Systems and methods for routing content to an associated output device
US20180025731A1 (en) * 2016-07-21 2018-01-25 Andrew Lovitt Cascading Specialized Recognition Engines Based on a Recognition Policy
KR102575634B1 (en) * 2016-07-26 2023-09-06 삼성전자주식회사 Electronic device and method for operating the same
KR102417046B1 (en) * 2016-10-21 2022-07-06 삼성전자주식회사 Device and method for providing recommended words for character input from user
WO2018074895A1 (en) 2016-10-21 2018-04-26 Samsung Electronics Co., Ltd. Device and method for providing recommended words for character input
US11204787B2 (en) 2017-01-09 2021-12-21 Apple Inc. Application integration with a digital assistant
US10748531B2 (en) * 2017-04-13 2020-08-18 Harman International Industries, Incorporated Management layer for multiple intelligent personal assistant services
US10580402B2 (en) 2017-04-27 2020-03-03 Microchip Technology Incorporated Voice-based control in a media system or other voice-controllable sound generating system
DK201770383A1 (en) 2017-05-09 2018-12-14 Apple Inc. User interface for correcting recognition errors
DK201770439A1 (en) * 2017-05-11 2018-12-13 Apple Inc. Offline personal assistant
DK180048B1 (en) 2017-05-11 2020-02-04 Apple Inc. MAINTAINING THE DATA PROTECTION OF PERSONAL INFORMATION
US10726832B2 (en) 2017-05-11 2020-07-28 Apple Inc. Maintaining privacy of personal information
DK179745B1 (en) 2017-05-12 2019-05-01 Apple Inc. SYNCHRONIZATION AND TASK DELEGATION OF A DIGITAL ASSISTANT
DK179496B1 (en) 2017-05-12 2019-01-15 Apple Inc. USER-SPECIFIC Acoustic Models
DK201770429A1 (en) 2017-05-12 2018-12-14 Apple Inc. Low-latency intelligent automated assistant
US10303715B2 (en) 2017-05-16 2019-05-28 Apple Inc. Intelligent automated assistant for media exploration
US20180336892A1 (en) 2017-05-16 2018-11-22 Apple Inc. Detecting a trigger of a digital assistant
US10607606B2 (en) * 2017-06-19 2020-03-31 Lenovo (Singapore) Pte. Ltd. Systems and methods for execution of digital assistant
KR101910385B1 (en) * 2017-06-22 2018-10-22 엘지전자 주식회사 Vehicle control device mounted on vehicle and method for controlling the vehicle
GB2578386B (en) 2017-06-27 2021-12-01 Cirrus Logic Int Semiconductor Ltd Detection of replay attack
GB201713697D0 (en) 2017-06-28 2017-10-11 Cirrus Logic Int Semiconductor Ltd Magnetic detection of replay attack
GB2563953A (en) 2017-06-28 2019-01-02 Cirrus Logic Int Semiconductor Ltd Detection of replay attack
GB201801528D0 (en) 2017-07-07 2018-03-14 Cirrus Logic Int Semiconductor Ltd Method, apparatus and systems for biometric processes
GB201801527D0 (en) 2017-07-07 2018-03-14 Cirrus Logic Int Semiconductor Ltd Method, apparatus and systems for biometric processes
GB201801532D0 (en) 2017-07-07 2018-03-14 Cirrus Logic Int Semiconductor Ltd Methods, apparatus and systems for audio playback
GB201801526D0 (en) 2017-07-07 2018-03-14 Cirrus Logic Int Semiconductor Ltd Methods, apparatus and systems for authentication
WO2019035504A1 (en) * 2017-08-16 2019-02-21 엘지전자 주식회사 Mobile terminal and control method thereof
KR102411766B1 (en) * 2017-08-25 2022-06-22 삼성전자주식회사 Method for activating voice recognition servive and electronic device for the same
KR20190033384A (en) * 2017-09-21 2019-03-29 삼성전자주식회사 Electronic apparatus for processing user utterance and control method thereof
GB201804843D0 (en) 2017-11-14 2018-05-09 Cirrus Logic Int Semiconductor Ltd Detection of replay attack
GB201801663D0 (en) 2017-10-13 2018-03-21 Cirrus Logic Int Semiconductor Ltd Detection of liveness
GB2567503A (en) 2017-10-13 2019-04-17 Cirrus Logic Int Semiconductor Ltd Analysing speech signals
GB201801664D0 (en) 2017-10-13 2018-03-21 Cirrus Logic Int Semiconductor Ltd Detection of liveness
GB201801661D0 (en) 2017-10-13 2018-03-21 Cirrus Logic International Uk Ltd Detection of liveness
US10665234B2 (en) * 2017-10-18 2020-05-26 Motorola Mobility Llc Detecting audio trigger phrases for a voice recognition session
GB201801659D0 (en) 2017-11-14 2018-03-21 Cirrus Logic Int Semiconductor Ltd Detection of loudspeaker playback
KR102071865B1 (en) * 2017-11-30 2020-01-31 주식회사 인텔로이드 Device and method for recognizing wake-up word using server recognition result
US11182122B2 (en) * 2017-12-08 2021-11-23 Amazon Technologies, Inc. Voice control of computing devices
US11475899B2 (en) 2018-01-23 2022-10-18 Cirrus Logic, Inc. Speaker identification
US11264037B2 (en) 2018-01-23 2022-03-01 Cirrus Logic, Inc. Speaker identification
US11735189B2 (en) 2018-01-23 2023-08-22 Cirrus Logic, Inc. Speaker identification
KR102459920B1 (en) 2018-01-25 2022-10-27 삼성전자주식회사 Application processor supporting low power echo cancellation, electronic device including the same and method of operating the same
US10818288B2 (en) 2018-03-26 2020-10-27 Apple Inc. Natural assistant interaction
US10928918B2 (en) 2018-05-07 2021-02-23 Apple Inc. Raise to speak
US11145294B2 (en) 2018-05-07 2021-10-12 Apple Inc. Intelligent automated assistant for delivering content from user experiences
DK180639B1 (en) 2018-06-01 2021-11-04 Apple Inc DISABILITY OF ATTENTION-ATTENTIVE VIRTUAL ASSISTANT
DK179822B1 (en) 2018-06-01 2019-07-12 Apple Inc. Voice interaction at a primary device to access call functionality of a companion device
US10892996B2 (en) 2018-06-01 2021-01-12 Apple Inc. Variable latency device coordination
KR102592769B1 (en) * 2018-07-20 2023-10-24 삼성전자주식회사 Electronic device and operating method thereof
US10692490B2 (en) 2018-07-31 2020-06-23 Cirrus Logic, Inc. Detection of replay attack
JP7167554B2 (en) * 2018-08-29 2022-11-09 富士通株式会社 Speech recognition device, speech recognition program and speech recognition method
US10915614B2 (en) 2018-08-31 2021-02-09 Cirrus Logic, Inc. Biometric authentication
US11037574B2 (en) 2018-09-05 2021-06-15 Cirrus Logic, Inc. Speaker recognition and speaker change detection
US11315553B2 (en) 2018-09-20 2022-04-26 Samsung Electronics Co., Ltd. Electronic device and method for providing or obtaining data for training thereof
US11462215B2 (en) 2018-09-28 2022-10-04 Apple Inc. Multi-modal inputs for voice commands
US11475898B2 (en) 2018-10-26 2022-10-18 Apple Inc. Low-latency multi-speaker speech recognition
JP7202853B2 (en) * 2018-11-08 2023-01-12 シャープ株式会社 refrigerator
US11638059B2 (en) 2019-01-04 2023-04-25 Apple Inc. Content playback on multiple devices
JP7225876B2 (en) * 2019-02-08 2023-02-21 富士通株式会社 Information processing device, arithmetic processing device, and control method for information processing device
US11741529B2 (en) * 2019-02-26 2023-08-29 Xenial, Inc. System for eatery ordering with mobile interface and point-of-sale terminal
US11348573B2 (en) 2019-03-18 2022-05-31 Apple Inc. Multimodality in digital assistant systems
US11423908B2 (en) 2019-05-06 2022-08-23 Apple Inc. Interpreting spoken requests
US11475884B2 (en) 2019-05-06 2022-10-18 Apple Inc. Reducing digital assistant latency when a language is incorrectly determined
US11307752B2 (en) 2019-05-06 2022-04-19 Apple Inc. User configurable task triggers
DK201970509A1 (en) 2019-05-06 2021-01-15 Apple Inc Spoken notifications
US11140099B2 (en) 2019-05-21 2021-10-05 Apple Inc. Providing message response suggestions
US11289073B2 (en) 2019-05-31 2022-03-29 Apple Inc. Device text to speech
DK201970511A1 (en) 2019-05-31 2021-02-15 Apple Inc Voice identification in digital assistant systems
US11496600B2 (en) 2019-05-31 2022-11-08 Apple Inc. Remote execution of machine-learned models
DK180129B1 (en) 2019-05-31 2020-06-02 Apple Inc. User activity shortcut suggestions
US11360641B2 (en) 2019-06-01 2022-06-14 Apple Inc. Increasing the relevance of new available information
US11468890B2 (en) 2019-06-01 2022-10-11 Apple Inc. Methods and user interfaces for voice-based control of electronic devices
US11488406B2 (en) 2019-09-25 2022-11-01 Apple Inc. Text detection using global geometry estimators
KR20210066647A (en) * 2019-11-28 2021-06-07 삼성전자주식회사 Electronic device and Method for controlling the electronic device thereof
DE102020200067A1 (en) * 2020-01-07 2021-07-08 Robert Bosch Gesellschaft mit beschränkter Haftung Device and method for operating voice assistants
KR20210136463A (en) 2020-05-07 2021-11-17 삼성전자주식회사 Electronic apparatus and controlling method thereof
US11043220B1 (en) 2020-05-11 2021-06-22 Apple Inc. Digital assistant hardware abstraction
US11061543B1 (en) 2020-05-11 2021-07-13 Apple Inc. Providing relevant data items based on context
US11755276B2 (en) 2020-05-12 2023-09-12 Apple Inc. Reducing description length based on confidence
US11490204B2 (en) 2020-07-20 2022-11-01 Apple Inc. Multi-device audio adjustment coordination
US11438683B2 (en) 2020-07-21 2022-09-06 Apple Inc. User identification using headphones
KR20220142757A (en) * 2021-04-15 2022-10-24 삼성전자주식회사 Electronic device and method for determining whether an object is in proximity in the electronic device
KR20230017971A (en) * 2021-07-28 2023-02-07 삼성전자주식회사 Electronic device and operation method thereof

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1365487A (en) * 1999-06-24 2002-08-21 西门子公司 Voice recognition method and device
CN1158645C (en) * 1998-10-16 2004-07-21 艾利森电话股份有限公司 Voice control of a user interface to service applications
CN1723487A (en) * 2002-12-13 2006-01-18 摩托罗拉公司 Method and apparatus for selective speech recognition
US20090204409A1 (en) * 2008-02-13 2009-08-13 Sensory, Incorporated Voice Interface and Search for Electronic Devices including Bluetooth Headsets and Remote Systems
CN103198831A (en) * 2013-04-10 2013-07-10 威盛电子股份有限公司 Voice control method and mobile terminal device

Family Cites Families (58)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB9415930D0 (en) 1994-08-04 1994-09-28 Forbo Nairn Ltd Floor coverings
US6070140A (en) 1995-06-05 2000-05-30 Tran; Bao Q. Speech recognizer
US7174299B2 (en) * 1995-08-18 2007-02-06 Canon Kabushiki Kaisha Speech recognition system, speech recognition apparatus, and speech recognition method
US5855000A (en) * 1995-09-08 1998-12-29 Carnegie Mellon University Method and apparatus for correcting and repairing machine-transcribed input using independent or cross-modal secondary input
WO2000058946A1 (en) * 1999-03-26 2000-10-05 Koninklijke Philips Electronics N.V. Client-server speech recognition
US6408272B1 (en) * 1999-04-12 2002-06-18 General Magic, Inc. Distributed voice user interface
JP2000322078A (en) 1999-05-14 2000-11-24 Sumitomo Electric Ind Ltd On-vehicle voice recognition device
US6963759B1 (en) * 1999-10-05 2005-11-08 Fastmobile, Inc. Speech recognition technique based on local interrupt detection
US20020046203A1 (en) * 2000-06-22 2002-04-18 The Sony Corporation/Sony Electronics Inc. Method and apparatus for providing ratings of web sites over the internet
FR2820872B1 (en) * 2001-02-13 2003-05-16 Thomson Multimedia Sa VOICE RECOGNITION METHOD, MODULE, DEVICE AND SERVER
US6738743B2 (en) * 2001-03-28 2004-05-18 Intel Corporation Unified client-server distributed architectures for spoken dialogue systems
US6898567B2 (en) * 2001-12-29 2005-05-24 Motorola, Inc. Method and apparatus for multi-level distributed speech recognition
JP2003241790A (en) * 2002-02-13 2003-08-29 Internatl Business Mach Corp <Ibm> Speech command processing system, computer device, speech command processing method, and program
DE10207895B4 (en) 2002-02-23 2005-11-03 Harman Becker Automotive Systems Gmbh Method for speech recognition and speech recognition system
US7386454B2 (en) * 2002-07-31 2008-06-10 International Business Machines Corporation Natural error handling in speech recognition
US7228275B1 (en) * 2002-10-21 2007-06-05 Toyota Infotechnology Center Co., Ltd. Speech recognition system having multiple speech recognizers
US7392182B2 (en) * 2002-12-18 2008-06-24 Harman International Industries, Inc. Speech recognition system
US7418392B1 (en) * 2003-09-25 2008-08-26 Sensory, Inc. System and method for controlling the operation of a device by voice commands
US6889189B2 (en) * 2003-09-26 2005-05-03 Matsushita Electric Industrial Co., Ltd. Speech recognizer performance in car and home applications utilizing novel multiple microphone configurations
US8589156B2 (en) * 2004-07-12 2013-11-19 Hewlett-Packard Development Company, L.P. Allocation of speech recognition tasks and combination of results thereof
US20060085199A1 (en) * 2004-10-19 2006-04-20 Yogendra Jain System and method for controlling the behavior of a device capable of speech recognition
ATE385024T1 (en) * 2005-02-21 2008-02-15 Harman Becker Automotive Sys MULTILINGUAL LANGUAGE RECOGNITION
US7899669B2 (en) * 2005-12-12 2011-03-01 Gregory John Gadbois Multi-voice speech recognition
US8234120B2 (en) * 2006-07-26 2012-07-31 Nuance Communications, Inc. Performing a safety analysis for user-defined voice commands to ensure that the voice commands do not cause speech recognition ambiguities
US8099287B2 (en) * 2006-12-05 2012-01-17 Nuance Communications, Inc. Automatically providing a user with substitutes for potentially ambiguous user-defined speech commands
US20110054900A1 (en) * 2007-03-07 2011-03-03 Phillips Michael S Hybrid command and control between resident and remote speech recognition facilities in a mobile voice-to-speech application
JP5310563B2 (en) * 2007-12-25 2013-10-09 日本電気株式会社 Speech recognition system, speech recognition method, and speech recognition program
US8364481B2 (en) * 2008-07-02 2013-01-29 Google Inc. Speech recognition with parallel recognition tasks
KR20100032140A (en) 2008-09-17 2010-03-25 주식회사 현대오토넷 Method of interactive voice recognition and apparatus for interactive voice recognition
US20120010890A1 (en) * 2008-12-30 2012-01-12 Raymond Clement Koverzin Power-optimized wireless communications device
US8892439B2 (en) * 2009-07-15 2014-11-18 Microsoft Corporation Combination and federation of local and remote speech recognition
US8311820B2 (en) * 2010-01-28 2012-11-13 Hewlett-Packard Development Company, L.P. Speech recognition based on noise level
KR101699720B1 (en) * 2010-08-03 2017-01-26 삼성전자주식회사 Apparatus for voice command recognition and method thereof
KR101192813B1 (en) * 2010-12-14 2012-10-26 (주)이엔엠시스템 Voice recognition system and method that performs voice recognition regarding low frequency domain sound in standby mode
US8930194B2 (en) * 2011-01-07 2015-01-06 Nuance Communications, Inc. Configurable speech recognition system using multiple recognizers
US8996381B2 (en) * 2011-09-27 2015-03-31 Sensory, Incorporated Background speech recognition assistant
US8340975B1 (en) * 2011-10-04 2012-12-25 Theodore Alfred Rosenberger Interactive speech recognition device and system for hands-free building control
US8972263B2 (en) * 2011-11-18 2015-03-03 Soundhound, Inc. System and method for performing dual mode speech recognition
KR101590332B1 (en) * 2012-01-09 2016-02-18 삼성전자주식회사 Imaging apparatus and controlling method thereof
US9129591B2 (en) * 2012-03-08 2015-09-08 Google Inc. Recognizing speech in multiple languages
US9117449B2 (en) * 2012-04-26 2015-08-25 Nuance Communications, Inc. Embedded system for construction of small footprint speech recognition with user-definable constraints
KR20130133629A (en) * 2012-05-29 2013-12-09 삼성전자주식회사 Method and apparatus for executing voice command in electronic device
US9142215B2 (en) * 2012-06-15 2015-09-22 Cypress Semiconductor Corporation Power-efficient voice activation
US9959865B2 (en) * 2012-11-13 2018-05-01 Beijing Lenovo Software Ltd. Information processing method with voice recognition
WO2014142702A1 (en) * 2013-03-15 2014-09-18 Obschestvo S Ogranichennoy Otvetstvennostiyu "Speaktoit" Selective speech recognition for chat and digital personal assistant systems
US10585568B1 (en) * 2013-02-22 2020-03-10 The Directv Group, Inc. Method and system of bookmarking content in a mobile device
US20140270260A1 (en) * 2013-03-13 2014-09-18 Aliphcom Speech detection using low power microelectrical mechanical systems sensor
US11151899B2 (en) * 2013-03-15 2021-10-19 Apple Inc. User training by intelligent digital assistant
EP2784774A1 (en) * 2013-03-29 2014-10-01 Orange Telephone voice personnal assistant
US9058805B2 (en) * 2013-05-13 2015-06-16 Google Inc. Multiple recognizer speech recognition
KR102394485B1 (en) * 2013-08-26 2022-05-06 삼성전자주식회사 Electronic device and method for voice recognition
US9245527B2 (en) * 2013-10-11 2016-01-26 Apple Inc. Speech recognition wake-up of a handheld portable electronic device
US20150169285A1 (en) * 2013-12-18 2015-06-18 Microsoft Corporation Intent-based user experience
CN105723451B (en) * 2013-12-20 2020-02-28 英特尔公司 Transition from low power always-on listening mode to high power speech recognition mode
CN105934791B (en) * 2014-01-31 2019-11-22 惠普发展公司，有限责任合伙企业 Voice input order
US9378740B1 (en) * 2014-09-30 2016-06-28 Amazon Technologies, Inc. Command suggestions during automatic speech recognition
US9775113B2 (en) * 2014-12-11 2017-09-26 Mediatek Inc. Voice wakeup detecting device with digital microphone and associated method
CN107134279B (en) * 2017-06-30 2020-06-19 百度在线网络技术（北京）有限公司 Voice awakening method, device, terminal and storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1158645C (en) * 1998-10-16 2004-07-21 艾利森电话股份有限公司 Voice control of a user interface to service applications
CN1365487A (en) * 1999-06-24 2002-08-21 西门子公司 Voice recognition method and device
CN1723487A (en) * 2002-12-13 2006-01-18 摩托罗拉公司 Method and apparatus for selective speech recognition
US20090204409A1 (en) * 2008-02-13 2009-08-13 Sensory, Incorporated Voice Interface and Search for Electronic Devices including Bluetooth Headsets and Remote Systems
CN103198831A (en) * 2013-04-10 2013-07-10 威盛电子股份有限公司 Voice control method and mobile terminal device

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107590096A (en) * 2017-08-31 2018-01-16 联想(北京)有限公司 Method and processor for processor in electronic equipment
CN107590096B (en) * 2017-08-31 2021-06-15 联想(北京)有限公司 Method for processor in electronic equipment and processor
CN112334977A (en) * 2018-08-14 2021-02-05 华为技术有限公司 Voice recognition method, wearable device and system
WO2020057467A1 (en) * 2018-09-20 2020-03-26 青岛海信电器股份有限公司 Information processing apparatus, information processing system and video apparatus
CN111199735A (en) * 2018-11-16 2020-05-26 阿尔派株式会社 Vehicle-mounted device and voice recognition method
CN110223696A (en) * 2019-05-22 2019-09-10 平安科技（深圳）有限公司 A kind of acquisition method of voice signal, device and terminal device
CN110223696B (en) * 2019-05-22 2024-04-05 平安科技（深圳）有限公司 Voice signal acquisition method and device and terminal equipment
CN110427097A (en) * 2019-06-18 2019-11-08 华为技术有限公司 Voice data processing method, apparatus and system
WO2020253715A1 (en) * 2019-06-18 2020-12-24 华为技术有限公司 Voice data processing method, device and system

Also Published As

Publication number Publication date
EP3040985B1 (en) 2023-08-23
KR20160055162A (en) 2016-05-17
US20220044690A1 (en) 2022-02-10
US20160217795A1 (en) 2016-07-28
KR102394485B1 (en) 2022-05-06
CN105493180B (en) 2019-08-30
EP3040985A4 (en) 2017-04-26
US10192557B2 (en) 2019-01-29
US11158326B2 (en) 2021-10-26
WO2015030474A1 (en) 2015-03-05
US20190228781A1 (en) 2019-07-25
EP3040985A1 (en) 2016-07-06

Similar Documents

Publication Publication Date Title
CN105493180A (en) Electronic device and method for voice recognition
US11664027B2 (en) Method of providing voice command and electronic device supporting the same
US10546587B2 (en) Electronic device and method for spoken interaction thereof
US10838765B2 (en) Task execution method for voice input and electronic device supporting the same
KR102208477B1 (en) Operating Method For Microphones and Electronic Device supporting the same
EP2816554A2 (en) Method of executing voice recognition of electronic device and electronic device using the same
US10706847B2 (en) Method for operating speech recognition service and electronic device supporting the same
US10811008B2 (en) Electronic apparatus for processing user utterance and server
EP3642838B1 (en) Method for operating speech recognition service and electronic device and server for supporting the same
KR20140139982A (en) Method for executing voice recognition and Electronic device using the same
US11537360B2 (en) System for processing user utterance and control method of same
US10594350B2 (en) Method of recognizing flip cover of electronic device, electronic device, and flip cover
CN104866065A (en) Low Power Driving Method And Electronic Device Performing Thereof
CN107925749A (en) Method and apparatus for the resolution ratio for adjusting electronic equipment
US11170764B2 (en) Electronic device for processing user utterance
KR20180109465A (en) Electronic device and method for screen controlling for processing user input using the same
US20200075008A1 (en) Voice data processing method and electronic device for supporting same
US11915700B2 (en) Device for processing user voice input
CN104950739A (en) Electronic device, audio device, and method for supplying power to the audio device
CN108293095A (en) Imaging sensor includes the electronic equipment and its operating method of the imaging sensor

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant